Merge branch 'main' into vision-support

.env.example

@@ -20,10 +20,12 @@ ALLOWED_TELEGRAM_USER_IDS=USER_ID_1,USER_ID_2
 # VISION_TOKEN_PRICE=0.01
 # ENABLE_QUOTING=true
 # ENABLE_IMAGE_GENERATION=true
+# ENABLE_TTS_GENERATION=true
 # ENABLE_TRANSCRIPTION=true
 # ENABLE_VISION=true
 # PROXY=http://localhost:8080
 # OPENAI_MODEL=gpt-3.5-turbo
+# OPENAI_BASE_URL=https://example.com/v1/
 # ASSISTANT_PROMPT="You are a helpful assistant."
 # SHOW_USAGE=false
 # STREAM=true
@@ -38,9 +40,15 @@ ALLOWED_TELEGRAM_USER_IDS=USER_ID_1,USER_ID_2
 # TEMPERATURE=1.0
 # PRESENCE_PENALTY=0.0
 # FREQUENCY_PENALTY=0.0
-# IMAGE_SIZE=512x512
+# IMAGE_MODEL=dall-e-3
+# IMAGE_QUALITY=hd
+# IMAGE_STYLE=natural
+# IMAGE_SIZE=1024x1024
+# IMAGE_FORMAT=document
 # VISION_DETAIL="low"
 # GROUP_TRIGGER_KEYWORD=""
 # IGNORE_GROUP_TRANSCRIPTIONS=true
 # IGNORE_GROUP_VISION=true
+# TTS_MODEL="tts-1"
+# TTS_VOICE="alloy"
 # BOT_LANGUAGE=en

README.md

@@ -30,12 +30,15 @@ A [Telegram bot](https://core.telegram.org/bots/api) that integrates with OpenAI
 - [x] GPT-4 support
   - If you have access to the GPT-4 API, simply change the `OPENAI_MODEL` parameter to `gpt-4`
 - [x] Localized bot language
-  - Available languages :gb: :de: :ru: :tr: :it: :finland: :es: :indonesia: :netherlands: :cn: :taiwan: :vietnam: :iran: :brazil: :ukraine: :malaysia:
+  - Available languages :gb: :de: :ru: :tr: :it: :finland: :es: :indonesia: :netherlands: :cn: :taiwan: :vietnam: :iran: :brazil: :ukraine: :malaysia: :uzbekistan:
 - [x] Improved inline queries support for group and private chats - by [@bugfloyd](https://github.com/bugfloyd)
   - To use this feature, enable inline queries for your bot in BotFather via the `/setinline` [command](https://core.telegram.org/bots/inline)
-- [x] (NEW!) Support *new models* [announced on June 13, 2023](https://openai.com/blog/function-calling-and-other-api-updates)
+- [x] Support *new models* [announced on June 13, 2023](https://openai.com/blog/function-calling-and-other-api-updates)
-- [x] (NEW!) Support *functions* (plugins) to extend the bot's functionality with 3rd party services
+- [x] Support *functions* (plugins) to extend the bot's functionality with 3rd party services
   - Weather, Spotify, Web search, text-to-speech and more. See [here](#available-plugins) for a list of available plugins
+- [x] Support unofficial OpenAI-compatible APIs - by [@kristaller486](https://github.com/kristaller486)
+- [x] (NEW!) Support GPT-4 Turbo and DALL·E 3 [announced on November 6, 2023](https://openai.com/blog/new-models-and-developer-products-announced-at-devday) - by [@AlexHTW](https://github.com/AlexHTW)
+- [x] (NEW!) Text-to-speech support [announced on November 6, 2023](https://platform.openai.com/docs/guides/text-to-speech) - by [@gilcu3](https://github.com/gilcu3)
 
 ## Additional features - help needed!
 If you'd like to help, check out the [issues](https://github.com/n3d1117/chatgpt-telegram-bot/issues) section and contribute!  
@@ -77,35 +80,43 @@ The following parameters are optional and can be set in the `.env` file:
 Check out the [Budget Manual](https://github.com/n3d1117/chatgpt-telegram-bot/discussions/184) for possible budget configurations.
 
 #### Additional optional configuration options
-| Parameter                          | Description                                                                                                                                                                                                                                                           | Default value                       |
+| Parameter                          | Description                                                                                                                                                                                                                                                                       | Default value                      |
-|------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------|
+|------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------------------------------------|
-| `ENABLE_QUOTING`                   | Whether to enable message quoting in private chats                                                                                                                                                                                                                    | `true`                              |
+| `ENABLE_QUOTING`                   | Whether to enable message quoting in private chats                                                                                                                                                                                                                                | `true`                             |
-| `ENABLE_IMAGE_GENERATION`          | Whether to enable image generation via the `/image` command                                                                                                                                                                                                           | `true`                              |
+| `ENABLE_IMAGE_GENERATION`          | Whether to enable image generation via the `/image` command                                                                                                                                                                                                                       | `true`                             |
-| `ENABLE_TRANSCRIPTION`             | Whether to enable transcriptions of audio and video messages                                                                                                                                                                                                          | `true`                              |
+| `ENABLE_TRANSCRIPTION`             | Whether to enable transcriptions of audio and video messages                                                                                                                                                                                                                      | `true`                             |
+| `ENABLE_TTS_GENERATION`            | Whether to enable text to speech generation via the `/tts`                                                                                                                                                                                                                        | `true`                             |
 | `ENABLE_VISION`             | Whether to enable vision capabilities in supported models                                                                                                                                                                                                          | `true`                              |
-| `PROXY`                            | Proxy to be used for OpenAI and Telegram bot (e.g. `http://localhost:8080`)                                                                                                                                                                                           | -                                   |
+| `PROXY`                            | Proxy to be used for OpenAI and Telegram bot (e.g. `http://localhost:8080`)                                                                                                                                                                                                       | -                                  |
-| `OPENAI_MODEL`                     | The OpenAI model to use for generating responses. You can find all available models [here](https://platform.openai.com/docs/models/)                                                                                                                                  | `gpt-3.5-turbo`                     |
+| `OPENAI_MODEL`                     | The OpenAI model to use for generating responses. You can find all available models [here](https://platform.openai.com/docs/models/)                                                                                                                                              | `gpt-3.5-turbo`                    |
-| `ASSISTANT_PROMPT`                 | A system message that sets the tone and controls the behavior of the assistant                                                                                                                                                                                        | `You are a helpful assistant.`      |
+| `OPENAI_BASE_URL`                  | Endpoint URL for unofficial OpenAI-compatible APIs (e.g., LocalAI or text-generation-webui)                                                                                                                                                                                       | Default OpenAI API URL             |
-| `SHOW_USAGE`                       | Whether to show OpenAI token usage information after each response                                                                                                                                                                                                    | `false`                             |
+| `ASSISTANT_PROMPT`                 | A system message that sets the tone and controls the behavior of the assistant                                                                                                                                                                                                    | `You are a helpful assistant.`     |
-| `STREAM`                           | Whether to stream responses. **Note**: incompatible, if enabled, with `N_CHOICES` higher than 1                                                                                                                                                                       | `true`                              |
+| `SHOW_USAGE`                       | Whether to show OpenAI token usage information after each response                                                                                                                                                                                                                | `false`                            |
-| `MAX_TOKENS`                       | Upper bound on how many tokens the ChatGPT API will return                                                                                                                                                                                                            | `1200` for GPT-3, `2400` for GPT-4  |
+| `STREAM`                           | Whether to stream responses. **Note**: incompatible, if enabled, with `N_CHOICES` higher than 1                                                                                                                                                                                   | `true`                             |
+| `MAX_TOKENS`                       | Upper bound on how many tokens the ChatGPT API will return                                                                                                                                                                                                                        | `1200` for GPT-3, `2400` for GPT-4 |
 | `VISION_MAX_TOKENS`                       | Upper bound on how many tokens vision models will return                                                                                                                                                                                                            | `300` for gpt-4-vision-preview  |
-| `MAX_HISTORY_SIZE`                 | Max number of messages to keep in memory, after which the conversation will be summarised to avoid excessive token usage                                                                                                                                              | `15`                                |
+| `MAX_HISTORY_SIZE`                 | Max number of messages to keep in memory, after which the conversation will be summarised to avoid excessive token usage                                                                                                                                                          | `15`                               |
-| `MAX_CONVERSATION_AGE_MINUTES`     | Maximum number of minutes a conversation should live since the last message, after which the conversation will be reset                                                                                                                                               | `180`                               |
+| `MAX_CONVERSATION_AGE_MINUTES`     | Maximum number of minutes a conversation should live since the last message, after which the conversation will be reset                                                                                                                                                           | `180`                              |
-| `VOICE_REPLY_WITH_TRANSCRIPT_ONLY` | Whether to answer to voice messages with the transcript only or with a ChatGPT response of the transcript                                                                                                                                                             | `false`                             |
+| `VOICE_REPLY_WITH_TRANSCRIPT_ONLY` | Whether to answer to voice messages with the transcript only or with a ChatGPT response of the transcript                                                                                                                                                                         | `false`                            |
-| `VOICE_REPLY_PROMPTS`              | A semicolon separated list of phrases (i.e. `Hi bot;Hello chat`). If the transcript starts with any of them, it will be treated as a prompt even if `VOICE_REPLY_WITH_TRANSCRIPT_ONLY` is set to `true`                                                               | -                                   |
+| `VOICE_REPLY_PROMPTS`              | A semicolon separated list of phrases (i.e. `Hi bot;Hello chat`). If the transcript starts with any of them, it will be treated as a prompt even if `VOICE_REPLY_WITH_TRANSCRIPT_ONLY` is set to `true`                                                                           | -                                  |
 | `VISION_PROMPT`              | A phrase (i.e. `What is in this image`). The vision models use it as prompt to interpret a given image. If there is caption in the image sent to the bot, that supersedes this parameter                                                               | `What is in this image`                                   |
-| `N_CHOICES`                        | Number of answers to generate for each input message. **Note**: setting this to a number higher than 1 will not work properly if `STREAM` is enabled                                                                                                                  | `1`                                 |
+| `N_CHOICES`                        | Number of answers to generate for each input message. **Note**: setting this to a number higher than 1 will not work properly if `STREAM` is enabled                                                                                                                              | `1`                                |
-| `TEMPERATURE`                      | Number between 0 and 2. Higher values will make the output more random                                                                                                                                                                                                | `1.0`                               |
+| `TEMPERATURE`                      | Number between 0 and 2. Higher values will make the output more random                                                                                                                                                                                                            | `1.0`                              |
-| `PRESENCE_PENALTY`                 | Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far                                                                                                                                                      | `0.0`                               |
+| `PRESENCE_PENALTY`                 | Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far                                                                                                                                                                  | `0.0`                              |
-| `FREQUENCY_PENALTY`                | Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far                                                                                                                                                 | `0.0`                               |
+| `FREQUENCY_PENALTY`                | Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far                                                                                                                                                             | `0.0`                              |
-| `IMAGE_SIZE`                       | The DALL·E generated image size. Allowed values: `256x256`, `512x512` or `1024x1024`                                                                                                                                                                                  | `512x512`                           |
+| `IMAGE_FORMAT`                     | The Telegram image receive mode. Allowed values: `document` or `photo`                                                                                                                                                                                                            | `photo`                            |
+| `IMAGE_MODEL`                      | The DALL·E model to be used. Available models: `dall-e-2` and `dall-e-3`, find current available models [here](https://platform.openai.com/docs/models/dall-e)                                                                                                                    | `dall-e-2`                         |
+| `IMAGE_QUALITY`                    | Quality of DALL·E images, only available for `dall-e-3`-model. Possible options: `standard` or `hd`, beware of [pricing differences](https://openai.com/pricing#image-models).                                                                                                    | `standard`                         |
+| `IMAGE_STYLE`                      | Style for DALL·E image generation, only available for `dall-e-3`-model. Possible options: `vivid` or `natural`. Check availbe styles [here](https://platform.openai.com/docs/api-reference/images/create).                                                                        | `vivid`                            |
+| `IMAGE_SIZE`                       | The DALL·E generated image size. Must be `256x256`, `512x512`, or `1024x1024` for dall-e-2. Must be `1024x1024` for dall-e-3 models.                                                                                                                                              | `512x512`                          |
 | `VISION_DETAIL`                       | The detail parameter for vision models, explained [Vision Guide](https://platform.openai.com/docs/guides/vision). Allowed values: `low` or `high`                                                                                                                                                                                  | `low`                           |
-| `GROUP_TRIGGER_KEYWORD`            | If set, the bot in group chats will only respond to messages that start with this keyword                                                                                                                                                                             | -                                   |
+| `GROUP_TRIGGER_KEYWORD`            | If set, the bot in group chats will only respond to messages that start with this keyword                                                                                                                                                                                         | -                                  |
-| `IGNORE_GROUP_TRANSCRIPTIONS`      | If set to true, the bot will not process transcriptions in group chats                                                                                                                                                                                                | `true`                              |
+| `IGNORE_GROUP_TRANSCRIPTIONS`      | If set to true, the bot will not process transcriptions in group chats                                                                                                                                                                                                            | `true`                             |
 | `IGNORE_GROUP_VISION`      | If set to true, the bot will not process vision queries in group chats                                                                                                                                                                                                | `true`                              |
-| `BOT_LANGUAGE`                     | Language of general bot messages. Currently available: `en`, `de`, `ru`, `tr`, `it`, `fi`, `es`, `id`, `nl`, `zh-cn`, `zh-tw`, `vi`, `fa`, `pt-br`, `uk`, `ms`.  [Contribute with additional translations](https://github.com/n3d1117/chatgpt-telegram-bot/discussions/219) | `en`                                |
+| `BOT_LANGUAGE`                     | Language of general bot messages. Currently available: `en`, `de`, `ru`, `tr`, `it`, `fi`, `es`, `id`, `nl`, `zh-cn`, `zh-tw`, `vi`, `fa`, `pt-br`, `uk`, `ms`, `uz`.  [Contribute with additional translations](https://github.com/n3d1117/chatgpt-telegram-bot/discussions/219) | `en`                               |
-| `WHISPER_PROMPT`                     | To improve the accuracy of Whisper's transcription service, especially for specific names or terms, you can set up a custom message.  [Speech to text - Prompting](https://platform.openai.com/docs/guides/speech-to-text/prompting) | `-`                                |
+| `WHISPER_PROMPT`                   | To improve the accuracy of Whisper's transcription service, especially for specific names or terms, you can set up a custom message.  [Speech to text - Prompting](https://platform.openai.com/docs/guides/speech-to-text/prompting)                                              | `-`                                |
+| `TTS_VOICE`                        | The Text to Speech voice to use. Allowed values: `alloy`, `echo`, `fable`, `onyx`, `nova`, or `shimmer`                                                                                                                                                                           | `alloy`                            |
+| `TTS_MODEL`                        | The Text to Speech model to use. Allowed values: `tts-1` or `tts-1-hd`                                                                                                                                                                                                            | `tts-1`                            |
 
 Check out the [official API reference](https://platform.openai.com/docs/api-reference/chat) for more details.
 

bot/main.py

@@ -41,6 +41,9 @@ def main():
         'max_tokens': int(os.environ.get('MAX_TOKENS', max_tokens_default)),
         'n_choices': int(os.environ.get('N_CHOICES', 1)),
         'temperature': float(os.environ.get('TEMPERATURE', 1.0)),
+        'image_model': os.environ.get('IMAGE_MODEL', 'dall-e-2'),
+        'image_quality': os.environ.get('IMAGE_QUALITY', 'standard'),
+        'image_style': os.environ.get('IMAGE_STYLE', 'vivid'),
         'image_size': os.environ.get('IMAGE_SIZE', '512x512'),
         'model': model,
         'enable_functions': os.environ.get('ENABLE_FUNCTIONS', str(functions_available)).lower() == 'true',
@@ -53,6 +56,8 @@ def main():
         'vision_prompt': os.environ.get('VISION_PROMPT', 'What is in this image'),
         'vision_detail': os.environ.get('VISION_DETAIL', 'low'),
         'vision_max_tokens': int(os.environ.get('VISION_MAX_TOKENS', '300')),
+        'tts_model': os.environ.get('TTS_MODEL', 'tts-1'),
+        'tts_voice': os.environ.get('TTS_VOICE', 'alloy'),
     }
 
     if openai_config['enable_functions'] and not functions_available:
@@ -74,6 +79,7 @@ def main():
         'enable_image_generation': os.environ.get('ENABLE_IMAGE_GENERATION', 'true').lower() == 'true',
         'enable_transcription': os.environ.get('ENABLE_TRANSCRIPTION', 'true').lower() == 'true',
         'enable_vision': os.environ.get('ENABLE_VISION', 'true').lower() == 'true',
+        'enable_tts_generation': os.environ.get('ENABLE_TTS_GENERATION', 'true').lower() == 'true',
         'budget_period': os.environ.get('BUDGET_PERIOD', 'monthly').lower(),
         'user_budgets': os.environ.get('USER_BUDGETS', os.environ.get('MONTHLY_USER_BUDGETS', '*')),
         'guest_budget': float(os.environ.get('GUEST_BUDGET', os.environ.get('MONTHLY_GUEST_BUDGET', '100.0'))),
@@ -87,6 +93,9 @@ def main():
         'token_price': float(os.environ.get('TOKEN_PRICE', 0.002)),
         'image_prices': [float(i) for i in os.environ.get('IMAGE_PRICES', "0.016,0.018,0.02").split(",")],
         'vision_token_price': float(os.environ.get('VISION_TOKEN_PRICE', '0.01')),
+        'image_receive_mode': os.environ.get('IMAGE_FORMAT', "photo"),
+        'tts_model': os.environ.get('TTS_MODEL', 'tts-1'),
+        'tts_prices': [float(i) for i in os.environ.get('TTS_PRICES', "0.015,0.030").split(",")],
         'transcription_price': float(os.environ.get('TRANSCRIPTION_PRICE', 0.006)),
         'bot_language': os.environ.get('BOT_LANGUAGE', 'en'),
     }

bot/openai_helper.py

@@ -10,6 +10,7 @@ import openai
 import requests
 import json
 import httpx
+import io
 from datetime import date
 from calendar import monthrange
 from PIL import Image
@@ -21,11 +22,12 @@ from plugin_manager import PluginManager
 
 # Models can be found here: https://platform.openai.com/docs/models/overview
 GPT_3_MODELS = ("gpt-3.5-turbo", "gpt-3.5-turbo-0301", "gpt-3.5-turbo-0613")
-GPT_3_16K_MODELS = ("gpt-3.5-turbo-16k", "gpt-3.5-turbo-16k-0613")
+GPT_3_16K_MODELS = ("gpt-3.5-turbo-16k", "gpt-3.5-turbo-16k-0613", "gpt-3.5-turbo-1106")
 GPT_4_MODELS = ("gpt-4", "gpt-4-0314", "gpt-4-0613")
 GPT_4_32K_MODELS = ("gpt-4-32k", "gpt-4-32k-0314", "gpt-4-32k-0613")
 GPT_4_VISION_MODELS = ("gpt-4-vision-preview",)
-GPT_ALL_MODELS = GPT_3_MODELS + GPT_3_16K_MODELS + GPT_4_MODELS + GPT_4_32K_MODELS + GPT_4_VISION_MODELS
+GPT_4_128K_MODELS = ("gpt-4-1106-preview",)
+GPT_ALL_MODELS = GPT_3_MODELS + GPT_3_16K_MODELS + GPT_4_MODELS + GPT_4_32K_MODELS + GPT_4_VISION_MODELS + GPT_4_128K_MODELS
 
 
 def default_max_tokens(model: str) -> int:
@@ -39,12 +41,16 @@ def default_max_tokens(model: str) -> int:
         return base
     elif model in GPT_4_MODELS:
         return base * 2
-    elif model in GPT_3_16K_MODELS:
+    elif model in GPT_3_16K_MODELS:    
+        if model == "gpt-3.5-turbo-1106":
+            return 4096
         return base * 4
     elif model in GPT_4_32K_MODELS:
         return base * 8
     elif model in GPT_4_VISION_MODELS:
         return 4096
+    elif model in GPT_4_128K_MODELS:
+        return 4096
 
 
 def are_functions_available(model: str) -> bool:
@@ -55,7 +61,7 @@ def are_functions_available(model: str) -> bool:
     if model in ("gpt-3.5-turbo-0301", "gpt-4-0314", "gpt-4-32k-0314"):
         return False
     # Stable models will be updated to support functions on June 27, 2023
-    if model in ("gpt-3.5-turbo", "gpt-4", "gpt-4-32k"):
+    if model in ("gpt-3.5-turbo", "gpt-3.5-turbo-1106", "gpt-4", "gpt-4-32k","gpt-4-1106-preview"):
         return datetime.date.today() > datetime.date(2023, 6, 27)
     if model == 'gpt-4-vision-preview':
         return False
@@ -326,6 +332,9 @@ class OpenAIHelper:
             response = await self.client.images.generate(
                 prompt=prompt,
                 n=1,
+                model=self.config['image_model'],
+                quality=self.config['image_quality'],
+                style=self.config['image_style'],
                 size=self.config['image_size']
             )
 
@@ -340,6 +349,28 @@ class OpenAIHelper:
         except Exception as e:
             raise Exception(f"⚠️ _{localized_text('error', bot_language)}._ ⚠️\n{str(e)}") from e
 
+    async def generate_speech(self, text: str) -> tuple[any, int]:
+        """
+        Generates an audio from the given text using TTS model.
+        :param prompt: The text to send to the model
+        :return: The audio in bytes and the text size
+        """
+        bot_language = self.config['bot_language']
+        try:
+            response = await self.client.audio.speech.create(
+                model=self.config['tts_model'],
+                voice=self.config['tts_voice'],
+                input=text,
+                response_format='opus'
+            )
+
+            temp_file = io.BytesIO()
+            temp_file.write(response.read())
+            temp_file.seek(0)
+            return temp_file, len(text)
+        except Exception as e:
+            raise Exception(f"⚠️ _{localized_text('error', bot_language)}._ ⚠️\n{str(e)}") from e
+
     async def transcribe(self, filename):
         """
         Transcribes the audio file using the Whisper model.
@@ -372,7 +403,7 @@ class OpenAIHelper:
             message = {'role':'user', 'content':[{'type':'text', 'text':prompt}, {'type':'image_url', \
                         'image_url': {'url':f'data:image/jpeg;base64,{image}', 'detail':self.config['vision_detail'] } }]}
             common_args = {
-                'model': self.config['model'],
+                'model': 'gpt-4-vision-preview', # the only one that currently makes sense here
                 'messages': self.conversations[chat_id] + [message],
                 'temperature': self.config['temperature'],
                 'n': 1, # several choices is not implemented yet
@@ -451,7 +482,7 @@ class OpenAIHelper:
             messages=messages,
             temperature=0.4
         )
-        return response.choices[0]['message']['content']
+        return response.choices[0].message.content
 
     def __max_model_tokens(self):
         base = 4096
@@ -465,6 +496,8 @@ class OpenAIHelper:
             return base * 8
         if self.config['model'] in GPT_4_VISION_MODELS:
             return base * 31
+        if self.config['model'] in GPT_4_128K_MODELS:
+            return base * 31
         raise NotImplementedError(
             f"Max tokens for model {self.config['model']} is not implemented yet."
         )
@@ -485,7 +518,7 @@ class OpenAIHelper:
         if model in GPT_3_MODELS + GPT_3_16K_MODELS:
             tokens_per_message = 4  # every message follows <|start|>{role/name}\n{content}<|end|>\n
             tokens_per_name = -1  # if there's a name, the role is omitted
-        elif model in GPT_4_MODELS + GPT_4_32K_MODELS + GPT_4_VISION_MODELS:
+        elif model in GPT_4_MODELS + GPT_4_32K_MODELS + GPT_4_VISION_MODELS + GPT_4_128K_MODELS:
             tokens_per_message = 3
             tokens_per_name = 1
         else:
@@ -507,9 +540,9 @@ class OpenAIHelper:
         :return: the number of tokens required
         """
         image = Image.open(fileobj)
-        model = self.config['model']
+        model = 'gpt-4-vision-preview' # fixed for now
         if model not in GPT_4_VISION_MODELS:
-            raise NotImplementedError(f"""num_tokens_from_messages() is not implemented for model {model}.""")
+            raise NotImplementedError(f"""count_tokens_vision() is not implemented for model {model}.""")
         
         w, h = image.size
         if w > h: w, h = h, w

bot/telegram_bot.py

@@ -48,6 +48,9 @@ class ChatGPTTelegramBot:
         if self.config.get('enable_image_generation', False):
             self.commands.append(BotCommand(command='image', description=localized_text('image_description', bot_language)))
 
+        if self.config.get('enable_tts_generation', False):
+            self.commands.append(BotCommand(command='tts', description=localized_text('tts_description', bot_language)))
+
         self.group_commands = [BotCommand(
             command='chat', description=localized_text('chat_description', bot_language)
         )] + self.commands
@@ -97,6 +100,7 @@ class ChatGPTTelegramBot:
         (transcribe_minutes_today, transcribe_seconds_today, transcribe_minutes_month,
          transcribe_seconds_month) = self.usage[user_id].get_current_transcription_duration()
         vision_today, vision_month = self.usage[user_id].get_current_vision_tokens()
+        characters_today, characters_month = self.usage[user_id].get_current_tts_usage()
         current_cost = self.usage[user_id].get_current_cost()
 
         chat_id = update.effective_chat.id
@@ -119,12 +123,17 @@ class ChatGPTTelegramBot:
         text_today_vision = ""
         if self.config.get('enable_vision', False):
             text_today_vision = f"{vision_today} {localized_text('stats_vision', bot_language)}\n"
+
+        text_today_tts = ""
+        if self.config.get('enable_tts_generation', False):
+            text_today_tts = f"{characters_today} {localized_text('stats_tts', bot_language)}\n"
         
         text_today = (
             f"*{localized_text('usage_today', bot_language)}:*\n"
             f"{tokens_today} {localized_text('stats_tokens', bot_language)}\n"
             f"{text_today_images}"  # Include the image statistics for today if applicable
             f"{text_today_vision}"
+            f"{text_today_tts}"
             f"{transcribe_minutes_today} {localized_text('stats_transcribe', bot_language)[0]} "
             f"{transcribe_seconds_today} {localized_text('stats_transcribe', bot_language)[1]}\n"
             f"{localized_text('stats_total', bot_language)}{current_cost['cost_today']:.2f}\n"
@@ -138,6 +147,10 @@ class ChatGPTTelegramBot:
         text_month_vision = ""
         if self.config.get('enable_vision', False):
             text_month_vision = f"{vision_month} {localized_text('stats_vision', bot_language)}\n"
+
+        text_month_tts = ""
+        if self.config.get('enable_tts_generation', False):
+            text_month_tts = f"{characters_month} {localized_text('stats_tts', bot_language)}\n"
         
         # Check if image generation is enabled and, if so, generate the image statistics for the month
         text_month = (
@@ -145,6 +158,7 @@ class ChatGPTTelegramBot:
             f"{tokens_month} {localized_text('stats_tokens', bot_language)}\n"
             f"{text_month_images}"  # Include the image statistics for the month if applicable
             f"{text_month_vision}"
+            f"{text_month_tts}"
             f"{transcribe_minutes_month} {localized_text('stats_transcribe', bot_language)[0]} "
             f"{transcribe_seconds_month} {localized_text('stats_transcribe', bot_language)[1]}\n"
             f"{localized_text('stats_total', bot_language)}{current_cost['cost_month']:.2f}"
@@ -241,10 +255,18 @@ class ChatGPTTelegramBot:
         async def _generate():
             try:
                 image_url, image_size = await self.openai.generate_image(prompt=image_query)
-                await update.effective_message.reply_photo(
+                if self.config['image_receive_mode'] == 'photo':
-                    reply_to_message_id=get_reply_to_message_id(self.config, update),
+                    await update.effective_message.reply_photo(
-                    photo=image_url
+                        reply_to_message_id=get_reply_to_message_id(self.config, update),
-                )
+                        photo=image_url
+                    )
+                elif self.config['image_receive_mode'] == 'document':
+                    await update.effective_message.reply_document(
+                        reply_to_message_id=get_reply_to_message_id(self.config, update),
+                        document=image_url
+                    )
+                else:
+                    raise Exception(f"env variable IMAGE_RECEIVE_MODE has invalid value {self.config['image_receive_mode']}")
                 # add image request to users usage tracker
                 user_id = update.message.from_user.id
                 self.usage[user_id].add_image_request(image_size, self.config['image_prices'])
@@ -263,6 +285,52 @@ class ChatGPTTelegramBot:
 
         await wrap_with_indicator(update, context, _generate, constants.ChatAction.UPLOAD_PHOTO)
 
+    async def tts(self, update: Update, context: ContextTypes.DEFAULT_TYPE):
+        """
+        Generates an speech for the given input using TTS APIs
+        """
+        if not self.config['enable_tts_generation'] \
+                or not await self.check_allowed_and_within_budget(update, context):
+            return
+
+        tts_query = message_text(update.message)
+        if tts_query == '':
+            await update.effective_message.reply_text(
+                message_thread_id=get_thread_id(update),
+                text=localized_text('tts_no_prompt', self.config['bot_language'])
+            )
+            return
+
+        logging.info(f'New speech generation request received from user {update.message.from_user.name} '
+                     f'(id: {update.message.from_user.id})')
+
+        async def _generate():
+            try:
+                speech_file, text_length = await self.openai.generate_speech(text=tts_query)
+
+                await update.effective_message.reply_voice(
+                    reply_to_message_id=get_reply_to_message_id(self.config, update),
+                    voice=speech_file
+                )
+                speech_file.close()
+                # add image request to users usage tracker
+                user_id = update.message.from_user.id
+                self.usage[user_id].add_tts_request(text_length, self.config['tts_model'], self.config['tts_prices'])
+                # add guest chat request to guest usage tracker
+                if str(user_id) not in self.config['allowed_user_ids'].split(',') and 'guests' in self.usage:
+                    self.usage["guests"].add_tts_request(text_length, self.config['tts_model'], self.config['tts_prices'])
+
+            except Exception as e:
+                logging.exception(e)
+                await update.effective_message.reply_text(
+                    message_thread_id=get_thread_id(update),
+                    reply_to_message_id=get_reply_to_message_id(self.config, update),
+                    text=f"{localized_text('tts_fail', self.config['bot_language'])}: {str(e)}",
+                    parse_mode=constants.ParseMode.MARKDOWN
+                )
+
+        await wrap_with_indicator(update, context, _generate, constants.ChatAction.UPLOAD_VOICE)
+
     async def transcribe(self, update: Update, context: ContextTypes.DEFAULT_TYPE):
         """
         Transcribe audio messages.
@@ -909,6 +977,7 @@ class ChatGPTTelegramBot:
         application.add_handler(CommandHandler('reset', self.reset))
         application.add_handler(CommandHandler('help', self.help))
         application.add_handler(CommandHandler('image', self.image))
+        application.add_handler(CommandHandler('tts', self.tts))
         application.add_handler(CommandHandler('start', self.help))
         application.add_handler(CommandHandler('stats', self.stats))
         application.add_handler(CommandHandler('resend', self.resend))

bot/usage_tracker.py

@@ -56,8 +56,10 @@ class UsageTracker:
         if os.path.isfile(self.user_file):
             with open(self.user_file, "r") as file:
                 self.usage = json.load(file)
-                if 'vision_tokens' not in self.usage['usage_history']:
+            if 'vision_tokens' not in self.usage['usage_history']:
-                    self.usage['usage_history']['vision_tokens'] = {}
+                self.usage['usage_history']['vision_tokens'] = {}
+            if 'tts_characters' not in self.usage['usage_history']:
+                self.usage['usage_history']['tts_characters'] = {}
         else:
             # ensure directory exists
             pathlib.Path(logs_dir).mkdir(exist_ok=True)
@@ -65,7 +67,7 @@ class UsageTracker:
             self.usage = {
                 "user_name": user_name,
                 "current_cost": {"day": 0.0, "month": 0.0, "all_time": 0.0, "last_update": str(date.today())},
-                "usage_history": {"chat_tokens": {}, "transcription_seconds": {}, "number_images": {}, "vision_tokens":{}}
+                "usage_history": {"chat_tokens": {}, "transcription_seconds": {}, "number_images": {}, "tts_characters": {}, "vision_tokens":{}}
             }
 
     # token usage functions:
@@ -194,6 +196,57 @@ class UsageTracker:
                 tokens_month += tokens
         return tokens_day, tokens_month
 
+    # tts usage functions:
+
+    def add_tts_request(self, text_length, tts_model, tts_prices):
+        tts_models = ['tts-1', 'tts-1-hd']
+        price = tts_prices[tts_models.index(tts_model)]
+        today = date.today()
+        tts_price = round(text_length * price / 1000, 2)
+        self.add_current_costs(tts_price)
+
+        if 'tts_characters' not in self.usage['usage_history']:
+            self.usage['usage_history']['tts_characters'] = {}
+        
+        if tts_model not in self.usage['usage_history']['tts_characters']:
+            self.usage['usage_history']['tts_characters'][tts_model] = {}
+
+        # update usage_history
+        if str(today) in self.usage["usage_history"]["tts_characters"][tts_model]:
+            # add requested text length to existing date
+            self.usage["usage_history"]["tts_characters"][tts_model][str(today)] += text_length
+        else:
+            # create new entry for current date
+            self.usage["usage_history"]["tts_characters"][tts_model][str(today)] = text_length
+
+        # write updated token usage to user file
+        with open(self.user_file, "w") as outfile:
+            json.dump(self.usage, outfile)
+
+    def get_current_tts_usage(self):
+        """Get length of speech generated for today and this month.
+
+        :return: total amount of characters converted to speech per day and per month
+        """
+
+        tts_models = ['tts-1', 'tts-1-hd']
+        today = date.today()
+        characters_day = 0
+        for tts_model in tts_models:
+            if tts_model in self.usage["usage_history"]["tts_characters"] and \
+                str(today) in self.usage["usage_history"]["tts_characters"][tts_model]:
+                characters_day += self.usage["usage_history"]["tts_characters"][tts_model][str(today)]
+
+        month = str(today)[:7]  # year-month as string
+        characters_month = 0
+        for tts_model in tts_models:
+            if tts_model in self.usage["usage_history"]["tts_characters"]: 
+                for today, characters in self.usage["usage_history"]["tts_characters"][tts_model].items():
+                    if today.startswith(month):
+                        characters_month += characters
+        return int(characters_day), int(characters_month)
+
+
     # transcription usage functions:
 
     def add_transcription_seconds(self, seconds, minute_price=0.006):
@@ -279,14 +332,15 @@ class UsageTracker:
         cost_all_time = self.usage["current_cost"].get("all_time", self.initialize_all_time_cost())
         return {"cost_today": cost_day, "cost_month": cost_month, "cost_all_time": cost_all_time}
 
-    def initialize_all_time_cost(self, tokens_price=0.002, image_prices="0.016,0.018,0.02", minute_price=0.006, vision_token_price=0.01):
+    def initialize_all_time_cost(self, tokens_price=0.002, image_prices="0.016,0.018,0.02", minute_price=0.006, vision_token_price=0.01, tts_prices='0.015,0.030'):
         """Get total USD amount of all requests in history
         
         :param tokens_price: price per 1000 tokens, defaults to 0.002
         :param image_prices: prices for images of sizes ["256x256", "512x512", "1024x1024"],
             defaults to [0.016, 0.018, 0.02]
         :param minute_price: price per minute transcription, defaults to 0.006
-        :param vision_token_price: price per 1k vision token interpretation, defaults to 0.01
+        :param vision_token_price: price per 1K vision token interpretation, defaults to 0.01
+        :param tts_prices: price per 1K characters tts per model ['tts-1', 'tts-1-hd'], defaults to [0.015, 0.030]
         :return: total cost of all requests
         """
         total_tokens = sum(self.usage['usage_history']['chat_tokens'].values())
@@ -302,5 +356,9 @@ class UsageTracker:
         total_vision_tokens = sum(self.usage['usage_history']['vision_tokens'].values())
         vision_cost = round(total_vision_tokens * vision_token_price / 1000, 2)
 
-        all_time_cost = token_cost + transcription_cost + image_cost + vision_cost
+        total_characters = [sum(tts_model.values()) for tts_model in self.usage['usage_history']['tts_characters'].values()]
+        tts_prices_list = [float(x) for x in tts_prices.split(',')]
+        tts_cost = round(sum([count * price / 1000 for count, price in zip(total_characters, tts_prices_list)]), 2)
+
+        all_time_cost = token_cost + transcription_cost + image_cost + vision_cost + tts_cost
         return all_time_cost

requirements.txt

@@ -1,7 +1,7 @@
 python-dotenv~=1.0.0
 pydub~=0.25.1
 tiktoken==0.5.1
-openai==1.1.1
+openai==1.3.3
 python-telegram-bot==20.3
 requests~=2.31.0
 tenacity==8.2.2
@@ -11,4 +11,4 @@ spotipy~=2.23.0
 pytube~=15.0.0
 gtts~=2.3.2
 whois~=0.9.27
-Pillow~=10.1.0
+Pillow~=10.1.0

translations.json

@@ -3,6 +3,7 @@
         "help_description":"Show help message",
         "reset_description":"Reset the conversation. Optionally pass high-level instructions (e.g. /reset You are a helpful assistant)",
         "image_description":"Generate image from prompt (e.g. /image cat)",
+        "tts_description":"Generate speech from text (e.g. /tts my house)",
         "stats_description":"Get your current usage statistics",
         "resend_description":"Resend the latest message",
         "chat_description":"Chat with the bot!",
@@ -15,6 +16,7 @@
         "stats_tokens":"tokens",
         "stats_images":"images generated",
         "stats_vision":"image tokens interpreted",
+        "stats_tts":"characters converted to speech",
         "stats_transcribe":["minutes and", "seconds transcribed"],
         "stats_total":"💰 For a total amount of $",
         "stats_budget":"Your remaining budget",
@@ -27,6 +29,8 @@
         "image_no_prompt":"Please provide a prompt! (e.g. /image cat)",
         "image_fail":"Failed to generate image",
         "vision_fail":"Failed to interpret image",
+        "tts_no_prompt":"Please provide text! (e.g. /tts my house)",
+        "tts_fail":"Failed to generate speech",
         "media_download_fail":["Failed to download audio file", "Make sure the file is not too large. (max 20MB)"],
         "media_type_fail":"Unsupported file type",
         "transcript":"Transcript",
@@ -48,6 +52,7 @@
         "help_description":"Muestra el mensaje de ayuda",
         "reset_description":"Reinicia la conversación. Opcionalmente, pasa instrucciones de alto nivel (por ejemplo, /reset Eres un asistente útil)",
         "image_description":"Genera una imagen a partir de una sugerencia (por ejemplo, /image gato)",
+        "tts_description":"Genera voz a partir de texto (por ejemplo, /tts mi casa)",
         "stats_description":"Obtén tus estadísticas de uso actuales",
         "resend_description":"Reenvía el último mensaje",
         "chat_description":"¡Chatea con el bot!",
@@ -59,6 +64,7 @@
         "usage_month":"Uso este mes",
         "stats_tokens":"tokens de chat usados",
         "stats_images":"imágenes generadas",
+        "stats_tts":"caracteres convertidos a voz",
         "stats_transcribe":["minutos y", "segundos transcritos"],
         "stats_total":"💰 Por un monto total de $",
         "stats_budget":"Tu presupuesto restante",
@@ -70,6 +76,8 @@
         "reset_done":"¡Listo!",
         "image_no_prompt":"¡Por favor proporciona una sugerencia! (por ejemplo, /image gato)",
         "image_fail":"No se pudo generar la imagen",
+        "tts_no_prompt":"¡Por favor proporciona texto! (por ejemplo, /tts mi casa)",
+        "tts_fail":"No se pudo generar la voz",
         "media_download_fail":["No se pudo descargar el archivo de audio", "Asegúrate de que el archivo no sea demasiado grande. (máx. 20MB)"],
         "media_type_fail":"Tipo de archivo no compatible",
         "transcript":"Transcripción",
@@ -91,6 +99,7 @@
         "help_description": "Mostra a mensagem de ajuda",
         "reset_description": "Redefine a conversa. Opcionalmente, passe instruções de alto nível (por exemplo, /reset Você é um assistente útil)",
         "image_description": "Gera uma imagem a partir do prompt (por exemplo, /image gato)",
+        "tts_description": "Gera fala a partir do texto (por exemplo, /tts minha casa)",
         "stats_description": "Obtenha suas estatísticas de uso atuais",
         "resend_description": "Reenvia a última mensagem",
         "chat_description": "Converse com o bot!",
@@ -102,6 +111,7 @@
         "usage_month": "Uso este mês",
         "stats_tokens": "tokens de chat usados",
         "stats_images": "imagens geradas",
+        "stats_tts": "caracteres convertidos em fala",
         "stats_transcribe": ["minutos e", "segundos transcritos"],
         "stats_total": "💰 Para um valor total de $",
         "stats_budget": "Seu orçamento restante",
@@ -113,6 +123,8 @@
         "reset_done": "Feito!",
         "image_no_prompt": "Por favor, forneça um prompt! (por exemplo, /image gato)",
         "image_fail": "Falha ao gerar imagem",
+        "tts_no_prompt": "Por favor, forneça texto! (por exemplo, /tts minha casa)",
+        "tts_fail": "Falha ao gerar fala",
         "media_download_fail": ["Falha ao baixar arquivo de áudio", "Certifique-se de que o arquivo não seja muito grande. (máx. 20 MB)"],
         "media_type_fail": "Tipo de arquivo não suportado",
         "transcript": "Transcrição",
@@ -134,6 +146,7 @@
         "help_description":"Zeige die Hilfenachricht",
         "reset_description":"Setze die Konversation zurück. Optionale Eingabe einer grundlegenden Anweisung (z.B. /reset Du bist ein hilfreicher Assistent)",
         "image_description":"Erzeuge ein Bild aus einer Aufforderung (z.B. /image Katze)",
+        "tts_description":"Erzeuge Sprache aus Text (z.B. /tts mein Haus)",
         "stats_description":"Zeige aktuelle Benutzungstatistiken",
         "resend_description":"Wiederhole das Senden der letzten Nachricht",
         "chat_description":"Schreibe mit dem Bot!",
@@ -145,6 +158,7 @@
         "usage_month":"Nutzung diesen Monat",
         "stats_tokens":"Chat Tokens verwendet",
         "stats_images":"Bilder generiert",
+        "stats_tts":"Zeichen in Sprache umgewandelt",
         "stats_transcribe":["Minuten und", "Sekunden abgeschrieben"],
         "stats_total":"💰 Für einem Gesamtbetrag von $",
         "stats_budget":"Dein verbliebenes Budget",
@@ -156,6 +170,8 @@
         "reset_done":"Fertig!",
         "image_no_prompt":"Bitte füge eine Aufforderung hinzu (z.B. /image Katze)",
         "image_fail":"Fehler beim Generieren eines Bildes",
+        "tts_no_prompt":"Bitte füge Text hinzu! (z.B. /tts mein Haus)",
+        "tts_fail":"Fehler beim Generieren von Sprache",
         "media_download_fail":["Fehler beim Herunterladen der Audiodatei", "Die Datei könnte zu groß sein. (max 20MB)"],
         "media_type_fail":"Dateityp nicht unterstützt",
         "transcript":"Abschrift",
@@ -177,6 +193,7 @@
         "help_description":"Näytä ohjeet",
         "reset_description":"Nollaa keskustelu. Voit myös antaa korkean tason ohjeita (esim. /reset Olet avulias avustaja)",
         "image_description":"Luo kuva tekstistä (esim. /image kissa)",
+        "tts_description":"Muuta teksti puheeksi (esim. /tts taloni)",
         "stats_description":"Hae tämän hetken käyttötilastot",
         "resend_description":"Lähetä viimeisin viesti uudestaan",
         "chat_description":"Keskustele botin kanssa!",
@@ -188,6 +205,7 @@
         "usage_month":"Käyttö tässä kuussa",
         "stats_tokens":"viestipolettia käytetty",
         "stats_images":"kuvaa luotu",
+        "stats_tts":"merkkiä muutettu puheeksi",
         "stats_transcribe":["minuuttia ja", "sekuntia litteroitu"],
         "stats_total":"💰 Yhteensä $",
         "stats_budget":"Jäljellä oleva budjettisi",
@@ -199,6 +217,8 @@
         "reset_done":"Valmis!",
         "image_no_prompt":"Ole hyvä ja anna ohjeet! (esim. /image kissa)",
         "image_fail":"Kuvan luonti epäonnistui",
+        "tts_no_prompt":"Ole hyvä ja anna teksti! (esim. /tts taloni)",
+        "tts_fail":"Puheen luonti epäonnistui",
         "media_download_fail":["Äänitiedoston lataus epäonnistui", "Varmista että se ei ole liian iso. (enintään 20MB)"],
         "media_type_fail":"Tiedostomuoto ei tuettu",
         "transcript":"Litteroitu teksti",
@@ -220,6 +240,7 @@
         "help_description":"Показать справочное сообщение",
         "reset_description":"Перезагрузить разговор. По желанию передай общие инструкции (например, /reset ты полезный помощник)",
         "image_description":"Создать изображение по запросу (например, /image кошка)",
+        "tts_description":"Создать речь из текста (например, /tts мой дом)",
         "stats_description":"Получить статистику использования",
         "resend_description":"Повторная отправка последнего сообщения",
         "chat_description":"Общайся с ботом!",
@@ -231,6 +252,7 @@
         "usage_month":"Использование в этом месяце",
         "stats_tokens":"токенов чата использовано",
         "stats_images":"изображений создано",
+        "stats_tts":"символов преобразовано в речь",
         "stats_transcribe":["минут(ы) и", "секунд(ы) расшифровки"],
         "stats_total":"💰 На общую сумму $",
         "stats_budget":"Остаточный бюджет",
@@ -242,6 +264,8 @@
         "reset_done":"Готово!",
         "image_no_prompt":"Пожалуйста, подайте запрос! (например, /image кошка)",
         "image_fail":"Не удалось создать изображение",
+        "tts_no_prompt":"Пожалуйста, подайте текст! (например, /tts мой дом)",
+        "tts_fail":"Не удалось создать речь",
         "media_download_fail":["Не удалось загрузить аудиофайл", "Проверьте, чтобы файл не был слишком большим. (не более 20 МБ)"],
         "media_type_fail":"Неподдержанный тип файла",
         "transcript":"Расшифровка",
@@ -263,6 +287,7 @@
         "help_description":"Yardım mesajını göster",
         "reset_description":"Konuşmayı sıfırla. İsteğe bağlı olarak botun nasıl davranacağını belirleyin (Örneğin: /reset Sen yardımcı bir asistansın)",
         "image_description":"Verilen komuta göre görüntü üret (Örneğin /image kedi)",
+        "tts_description":"Verilen metni seslendir (Örneğin /tts evim)",
         "stats_description":"Mevcut kullanım istatistiklerinizi alın",
         "resend_description":"En son mesajı yeniden gönder",
         "chat_description":"Bot ile sohbet edin!",
@@ -274,6 +299,7 @@
         "usage_month":"Bu ayki kullanım",
         "stats_tokens":"sohbet token'i kullanıldı",
         "stats_images":"görüntüler oluşturuldu",
+        "stats_tts":"seslendirilen karakterler",
         "stats_transcribe":["dakika", "saniye sesten yazıya çeviri yapıldı"],
         "stats_total":"💰 Bu kullanımların toplam maliyeti $",
         "stats_budget":"Kalan bütçeniz",
@@ -285,6 +311,8 @@
         "reset_done":"Tamamlandı!",
         "image_no_prompt":"Lütfen komut giriniz (Örneğin /image kedi)",
         "image_fail":"Görüntü oluşturulamadı",
+        "tts_no_prompt":"Lütfen metin giriniz (Örneğin /tts evim)",
+        "tts_fail":"Seslendirme oluşturulamadı",
         "media_download_fail":["Ses dosyası indirilemedi", "Dosyanın çok büyük olmadığından emin olun. (maksimum 20MB)"],
         "media_type_fail":"Desteklenmeyen dosya türü",
         "transcript":"Yazıya çevirilmiş hali",
@@ -306,6 +334,7 @@
         "help_description":"Mostra il messaggio di aiuto",
         "reset_description":"Resetta la conversazione. Puoi anche specificare ulteriori istruzioni (ad esempio, /reset Sei un assistente utile).",
         "image_description":"Genera immagine da un testo (ad es. /image gatto)",
+        "tts_description":"Genera audio da un testo (ad es. /tts la mia casa)",
         "stats_description":"Mostra le statistiche di utilizzo",
         "resend_description":"Reinvia l'ultimo messaggio",
         "chat_description":"Chatta con il bot!",
@@ -317,6 +346,7 @@
         "usage_month":"Utilizzo questo mese",
         "stats_tokens":"token utilizzati",
         "stats_images":"immagini generate",
+        "stats_tts":"caratteri convertiti in audio",
         "stats_transcribe":["minuti", "secondi trascritti"],
         "stats_total":"💰 Per un totale di $",
         "stats_budget":"Budget rimanente",
@@ -328,6 +358,8 @@
         "reset_done":"Fatto!",
         "image_no_prompt":"Inserisci un testo (ad es. /image gatto)",
         "image_fail":"Impossibile generare l'immagine",
+        "tts_no_prompt":"Inserisci un testo (ad es. /tts la mia casa)",
+        "tts_fail":"Impossibile generare l'audio",
         "media_download_fail":["Impossibile processare il file audio", "Assicurati che il file non sia troppo pesante (massimo 20MB)"],
         "media_type_fail":"Tipo di file non supportato",
         "transcript":"Trascrizione",
@@ -349,6 +381,7 @@
         "help_description": "Menampilkan pesan bantuan",
         "reset_description": "Merestart percakapan. Opsional memasukkan instruksi tingkat tinggi (misalnya /reset Anda adalah asisten yang membantu)",
         "image_description": "Menghasilkan gambar dari input prompt (misalnya /image kucing)",
+        "tts_description": "Menghasilkan suara dari teks (misalnya /tts rumah saya)",
         "stats_description": "Mendapatkan statistik penggunaan saat ini",
         "resend_description": "Mengirim kembali pesan terakhir",
         "chat_description": "Berkonversasi dengan bot!",
@@ -360,6 +393,7 @@
         "usage_month": "Penggunaan bulan ini",
         "stats_tokens": "token obrolan yang digunakan",
         "stats_images": "gambar yang dihasilkan",
+        "stats_tts": "karakter dikonversi ke suara",
         "stats_transcribe": ["menit dan", "detik ditranskripsi"],
         "stats_total": "💰 Untuk total sebesar $",
         "stats_budget": "Sisa anggaran Anda",
@@ -371,6 +405,8 @@
         "reset_done": "Selesai!",
         "image_no_prompt": "Harap berikan prompt! (misalnya /image kucing)",
         "image_fail": "Gagal menghasilkan gambar",
+        "tts_no_prompt": "Harap berikan teks! (misalnya /tts rumah saya)",
+        "tts_fail": "Gagal menghasilkan suara",
         "media_download_fail": ["Gagal mengunduh file audio", "Pastikan file tidak terlalu besar. (maksimal 20MB)"],
         "media_type_fail": "Tipe file tidak didukung",
         "transcript": "Transkrip",
@@ -392,6 +428,7 @@
         "help_description":"Toon uitleg",
         "reset_description":"Herstart het gesprek. Voeg eventueel instructies toe (bijv. /reset Je bent een behulpzame assistent)",
         "image_description":"Genereer een afbeelding van een prompt (bijv. /image kat)",
+        "tts_description":"Genereer spraak van tekst (bijv. /tts mijn huis)",
         "stats_description":"Bekijk je huidige gebruiksstatistieken",
         "resend_description":"Verstuur het laatste bericht opnieuw",
         "chat_description":"Chat met de bot!",
@@ -403,6 +440,7 @@
         "usage_month":"Gebruik deze maand",
         "stats_tokens":"chat tokens gebruikt",
         "stats_images":"afbeeldingen gegenereerd",
+        "stats_tts":"karakters omgezet naar spraak",
         "stats_transcribe":["minuten en", "seconden audio naar tekst omgezet"],
         "stats_total":"💰 Voor een totaal van $",
         "stats_budget":"Je resterende budget",
@@ -414,6 +452,8 @@
         "reset_done":"Klaar!",
         "image_no_prompt":"Geef a.u.b. een prompt! (bijv. /image kat)",
         "image_fail":"Afbeelding genereren mislukt",
+        "tts_no_prompt":"Geef a.u.b. tekst! (bijv. /tts mijn huis)",
+        "tts_fail":"Spraak genereren mislukt",
         "media_download_fail":["Audio bestand downloaden mislukt", "Check of het niet te groot is. (max 20MB)"],
         "media_type_fail":"Niet ondersteund bestandsformaat",
         "transcript":"Uitgeschreven tekst",
@@ -435,6 +475,7 @@
         "help_description":"显示帮助信息",
         "reset_description":"重置对话。可以选择传递高级指令（例如/reset 你是一个有用的助手）",
         "image_description":"根据提示生成图像（例如/image 猫）",
+        "tts_description":"将文本转换为语音（例如/tts 我的房子）",
         "stats_description":"获取您当前的使用统计",
         "resend_description":"重新发送最近的消息",
         "chat_description":"与机器人聊天！",
@@ -446,6 +487,7 @@
         "usage_month":"本月使用情况",
         "stats_tokens":"使用的token",
         "stats_images":"生成图像的数量",
+        "stats_tts":"转换为语音的字符",
         "stats_transcribe":["分钟", "秒转录时长"],
         "stats_total":"💰 总计金额 $",
         "stats_budget":"您的剩余预算",
@@ -457,6 +499,8 @@
         "reset_done":"完成！",
         "image_no_prompt":"请提供提示！（例如/image 猫）",
         "image_fail":"生成图像失败",
+        "tts_no_prompt":"请提供文本！（例如/tts 我的房子）",
+        "tts_fail":"生成语音失败",
         "media_download_fail":["下载音频文件失败", "请确保文件不要太大（最大20MB）"],
         "media_type_fail":"不支持的文件类型",
         "transcript":"转录",
@@ -478,6 +522,7 @@
         "help_description":"顯示幫助訊息",
         "reset_description":"重設對話。可以選擇傳遞進階指令（例如 /reset 你是一個樂於助人的助手）",
         "image_description":"根據提示生成圖片（例如 /image 貓）",
+        "tts_description":"將文字轉換為語音（例如 /tts 我的房子）",
         "stats_description":"取得當前使用統計",
         "resend_description":"重新傳送最後一則訊息",
         "chat_description":"與機器人聊天！",
@@ -489,6 +534,7 @@
         "usage_month":"本月用量",
         "stats_tokens":"Token 已使用",
         "stats_images":"圖片已生成",
+        "stats_tts":"轉換為語音的字元",
         "stats_transcribe":["分", "秒已轉錄"],
         "stats_total":"💰 總計金額 $",
         "stats_budget":"剩餘預算",
@@ -500,6 +546,8 @@
         "reset_done":"重設完成！",
         "image_no_prompt":"請輸入提示！（例如 /image 貓）",
         "image_fail":"圖片生成失敗",
+        "tts_no_prompt":"請輸入文字！（例如 /tts 我的房子）",
+        "tts_fail":"語音生成失敗",
         "media_download_fail":["下載音訊檔案失敗", "請確保檔案大小不超過 20MB"],
         "media_type_fail":"不支援的檔案類型",
         "transcript":"轉錄",
@@ -521,6 +569,7 @@
         "help_description":"Hiển thị trợ giúp",
         "reset_description":"Đặt lại cuộc trò chuyện. Tùy ý chuyển hướng dẫn cấp cao (ví dụ: /reset Bạn là một trợ lý hữu ích)",
         "image_description":"Tạo hình ảnh từ câu lệnh (ví dụ: /image cat)",
+        "tts_description":"Tạo giọng nói từ văn bản (ví dụ: /tts nhà của tôi)",
         "stats_description":"Nhận số liệu thống kê sử dụng hiện tại của bạn",
         "resend_description":"Gửi lại tin nhắn mới nhất",
         "chat_description":"Trò chuyện với bot!",
@@ -532,6 +581,7 @@
         "usage_month":"Sử dụng trong tháng này",
         "stats_tokens":"mã thông báo trò chuyện được sử dụng",
         "stats_images":"hình ảnh tạo ra",
+        "stats_tts":"ký tự được chuyển đổi thành giọng nói",
         "stats_transcribe":["phút và", "giây"],
         "stats_total":"💰 Với tổng số tiền $",
         "stats_budget":"Ngân sách còn lại của bạn",
@@ -543,6 +593,8 @@
         "reset_done":"Xong!",
         "image_no_prompt":"Vui lòng cung cấp lời nhắc! (ví dụ: /image con mèo",
         "image_fail":"Không thể tạo hình ảnh",
+        "tts_no_prompt":"Vui lòng cung cấp văn bản! (ví dụ: /tts nhà của tôi)",
+        "tts_fail":"Không thể tạo giọng nói",
         "media_download_fail":["Không thể tải xuống tệp âm thanh", "Đảm bảo tệp không quá lớn. (tối đa 20 MB)"],
         "media_type_fail":"Loại tập tin không được hỗ trợ",
         "transcript":"Dịch",
@@ -564,6 +616,7 @@
         "help_description":"نمایش پیغام راهنما",
         "reset_description":"مکالمه را تنظیم مجدد کنید. به صورت اختیاری می‌توانید دستورالعمل های سطح بالا را ارسال کنید (به عنوان مثال /reset تو یک دستیار مفید هستی)",
         "image_description":"ایجاد تصویر بر اساس فرمان (به عنوان مثال /image گربه)",
+        "tts_description":"تبدیل متن به صدا (به عنوان مثال /tts خانه من)",
         "stats_description":"آمار استفاده فعلی خود را دریافت کنید",
         "resend_description":"آخرین پیام را دوباره ارسال کنید",
         "chat_description":"چت با ربات!",
@@ -575,6 +628,7 @@
         "usage_month":"استفاده این ماه",
         "stats_tokens":"توکن چت استفاده شده است",
         "stats_images":"تصویر تولید شده است",
+        "stats_tts":"کاراکترهای تبدیل شده به صدا",
         "stats_transcribe":["دقیقه و", "ثانیه رونویسی شده است"],
         "stats_total":"💰 مقدار کل مصرف: $",
         "stats_budget":"بودجه باقی‌مانده شما",
@@ -586,6 +640,8 @@
         "reset_done":"انجام شد!",
         "image_no_prompt":"لطفا یک فرمان ارائه دهید! (به عنوان مثال /image گربه)",
         "image_fail":"در تولید تصویر خطایی رخ داد",
+        "tts_no_prompt":"لطفا متنی را وارد کنید! (به عنوان مثال /tts خانه من)",
+        "tts_fail":"در تولید صدا خطایی رخ داد",
         "media_download_fail":["فایل صوتی دانلود نشد", "دقت کنید که فایل خیلی بزرگ نباشد. (حداکثر 20 مگابایت)"],
         "media_type_fail":"نوع فایل پشتیبانی نمی‌شود",
         "transcript":"رونوشت",
@@ -607,6 +663,7 @@
         "help_description":"Показати повідомлення допомоги",
         "reset_description":"Скинути розмову. Опціонально передайте високорівневі інструкції (наприклад, /reset Ви корисний помічник)",
         "image_description":"Створити зображення за вашим запитом (наприклад, /image кіт)",
+        "tts_description":"Створити голос з тексту (наприклад, /tts мій будинок)",
         "stats_description":"Отримати вашу поточну статистику використання",
         "resend_description":"Повторно відправити останнє повідомлення",
         "chat_description":"Розмовляйте з ботом!",
@@ -618,6 +675,7 @@
         "usage_month":"Використання цього місяця",
         "stats_tokens":"використано токенів чату",
         "stats_images":"згенеровано зображень",
+        "stats_tts":"символів перетворено на голос",
         "stats_transcribe":["хвилин і", "секунд транскрибовано"],
         "stats_total":"💰 Загальна сума $",
         "stats_budget":"Ваш залишок бюджету",
@@ -629,6 +687,8 @@
         "reset_done":"Готово!",
         "image_no_prompt":"Будь ласка, надайте свій запит! (наприклад, /image кіт)",
         "image_fail":"Не вдалося створити зображення",
+        "tts_no_prompt":"Будь ласка, надайте текст! (наприклад, /tts мій будинок)",
+        "tts_fail":"Не вдалося створити голос",
         "media_download_fail":["Не вдалося завантажити аудіофайл", "Переконайтеся, що файл не занадто великий. (максимум 20 МБ)"],
         "media_type_fail":"Непідтримуваний тип файлу",
         "transcript":"Транскрипт",
@@ -650,6 +710,7 @@
         "help_description":"Lihat Mesej Bantuan",
         "reset_description":"Tetapkan semula perbualan. Secara pilihan, hantar arahan peringkat tinggi (cth. /reset Anda adalah pembantu yang membantu)",
         "image_description":"Jana imej daripada gesaan (cth. /image cat)",
+        "tts_description":"Tukar teks kepada suara (cth. /tts rumah saya)",
         "stats_description":"Dapatkan statistik penggunaan semasa anda",
         "resend_description":"Hantar semula mesej terkini",
         "chat_description":"Sembang dengan bot!",
@@ -661,6 +722,7 @@
         "usage_month":"Penggunaan bulan ini",
         "stats_tokens":"Token",
         "stats_images":"Penghasilan",
+        "stats_tts":"Aksara yang ditukar kepada suara",
         "stats_transcribe":["Minit dan", "Penterjemah yang kedua"],
         "stats_total":"Jumlah semua 💰 dalam $",
         "stats_budget":"Baki yang tersisa",
@@ -672,6 +734,8 @@
         "reset_done":"Selesai!",
         "image_no_prompt":"Sila berikan gesaan! (cth. /image cat)",
         "image_fail":"Gagal menjana imej",
+        "tts_no_prompt":"Sila berikan teks! (cth. /tts rumah saya)",
+        "tts_fail":"Gagal menjana suara",
         "media_download_fail":["Gagal memuat turun fail audio", "Pastikan fail tidak terlalu besar. (maks 20MB)"],
         "media_type_fail":"Jenis fail tidak disokong",
         "transcript":"Transkrip",
@@ -688,5 +752,52 @@
         "ask_chatgpt":"Tanya ChatGPT",
         "loading":"Memuatkan...",
         "function_unavailable_in_inline_mode": "Fungsi ini tidak tersedia dalam mod sebaris"
+    },
+    "uz": {
+        "help_description": "Yordam xabarini ko'rsatish",
+        "reset_description": "Suhbatni qayta boshlang. Agar xohlasangiz, umumiy ko'rsatmalar bering (masalan, /reset siz foydali yordamchisiz)",
+        "image_description": "Tasvirni so'rov bo'yicha yaratish (masalan, /image mushuk)",
+        "tts_description": "Matnni ovozga aylantirish (masalan, /tts uyim)",
+        "stats_description": "Hozirgi foydalanilgan statistikani olish",
+        "resend_description": "Oxirgi xabarni qayta yuborish",
+        "chat_description": "Bot bilan suxbat!",
+        "disallowed": "Kechirasiz, sizga bu botdan foydalanish taqiqlangan. Siz manba kodini tekshirishingiz mumkin https://github.com/n3d1117/chatgpt-telegram-bot",
+        "budget_limit": "Kechirasiz, siz foydalanish chegarasiga yetdingiz.",
+        "help_text": ["Men ChatGPT botman, men bilan gaplashing!", "Menga ovozli xabar yoki fayl yuboring, men uni siz uchun transkripsiya qilaman", "Ochiq manba: https://github.com/n3d1117/chatgpt-telegram-bot"],
+        "stats_conversation": ["Hozirgi suhbat", "tarixdagi chat xabarlari", "tarixdagi suhbat tokenlari"],
+        "usage_today": "Bugungi foydalanish",
+        "usage_month": "Bu oydagi foydalanish",
+        "stats_tokens": "tokenlar",
+        "stats_images": "yaratilgan tasvirlar",
+        "stats_tts": "ovozga aylangan belgilar",
+        "stats_transcribe": ["minutlar va", "soniyalar transkripsiya qilingan"],
+        "stats_total": "💰 Jami miqdor $",
+        "stats_budget": "Qolgan budjetingiz",
+        "monthly": " bu oy uchun",
+        "daily": " bugun uchun",
+        "all-time": "",
+        "stats_openai": "Shu oyda OpenAI hisobingizdan to'lov amalga oshirildi $",
+        "resend_failed": "Sizda qayta yuborish uchun hech narsa yo'q",
+        "reset_done": "Bajarildi!",
+        "image_no_prompt": "Iltimos, so'rov yozing! (masalan, /image mushuk)",
+        "image_fail": "Tasvir yaratish amalga oshmadi",
+        "tts_no_prompt": "Iltimos, matn kiriting! (masalan, /tts uyim)",
+        "tts_fail": "Ovoz yaratish amalga oshmadi",
+        "media_download_fail": ["Audio faylni yuklab olish amalga oshmadi", "Fayl hajmi katta emasligiga ishonch hosil qiling. (max 20MB)"],
+        "media_type_fail": "Qo'llab-quvvatlanmaydigan fayl turi",
+        "transcript": "Transkript",
+        "answer": "Javob",
+        "transcribe_fail": "Matnni transkripsiya qilib bo'lmadi",
+        "chat_fail": "Javob olish amalga oshmadi",
+        "prompt": "so'rov",
+        "completion": "yakunlash",
+        "openai_rate_limit": "OpenAI ta'rif chegarasidan oshib ketdi",
+        "openai_invalid": "OpenAI So'rov noto'g'ri",
+        "error": "Xatolik yuz berdi",
+        "try_again": "Birozdan keyin qayta urinib ko'ring",
+        "answer_with_chatgpt": "ChatGPT bilan javob berish",
+        "ask_chatgpt": "ChatGPTdan so'rash",
+        "loading": "Yuklanmoqda...",
+        "function_unavailable_in_inline_mode": "Bu funksiya inline rejimida mavjud emas"
     }
 }