Merge branch 'feature/voice-chat-mode'

.env.example

@@ -11,4 +11,7 @@ ALLOWED_TELEGRAM_USER_IDS="USER_ID_1,USER_ID_2"
 SHOW_USAGE=false
 
 # Max number of messages to keep in memory, after which the conversation will be summarised
-MAX_HISTORY_SIZE=10
+MAX_HISTORY_SIZE=10
+
+# Whether to answer to voice messages with the transcript or with a ChatGPT response of the transcript
+VOICE_REPLY_WITH_TRANSCRIPT_ONLY=true

README.md

@@ -45,13 +45,15 @@ ALLOWED_TELEGRAM_USER_IDS="USER_ID_1,USER_ID_2,..." # Defaults to "*" (everyone)
 PROXY="YOUR_PROXY" # e.g. "http://localhost:8080", defaults to none
 SHOW_USAGE=true # Defaults to false
 MAX_HISTORY_SIZE=15 # Defaults to 10
+VOICE_REPLY_WITH_TRANSCRIPT_ONLY=false # Defaults to true
 ```
 * `OPENAI_API_KEY`: Your OpenAI API key, you can get it from [here](https://platform.openai.com/account/api-keys)
 * `TELEGRAM_BOT_TOKEN`: Your Telegram bot's token, obtained using [BotFather](http://t.me/botfather) (see [tutorial](https://core.telegram.org/bots/tutorial#obtain-your-bot-token))
 * `ALLOWED_TELEGRAM_USER_IDS`: A comma-separated list of Telegram user IDs that are allowed to interact with the bot (use [getidsbot](https://t.me/getidsbot) to find your user ID). **Note**: by default, *everyone* is allowed (`*`)
 * `PROXY`: Proxy to be used for OpenAI and Telegram bot
 * `SHOW_USAGE`: Whether to show OpenAI token usage information after each response
 * `MAX_HISTORY_SIZE`: Max number of messages to keep in memory, after which the conversation will be summarised to avoid excessive token usage ([#34](https://github.com/n3d1117/chatgpt-telegram-bot/issues/34))
+* `VOICE_REPLY_WITH_TRANSCRIPT_ONLY`: Whether to answer to voice messages with the transcript only or with a ChatGPT response of the transcript ([#38](https://github.com/n3d1117/chatgpt-telegram-bot/issues/38))
 
 Additional model parameters can be configured from the `main.py` file:
 ```python

main.py

@@ -62,7 +62,8 @@ def main():
  telegram_config = {
  'token': os.environ['TELEGRAM_BOT_TOKEN'],
  'allowed_user_ids': os.environ.get('ALLOWED_TELEGRAM_USER_IDS', '*'),
- 'proxy': os.environ.get('PROXY', None)
+ 'proxy': os.environ.get('PROXY', None),
+ 'voice_reply_transcript': os.environ.get('VOICE_REPLY_WITH_TRANSCRIPT_ONLY', 'true').lower() == 'true',
  }
 
  # Setup and run ChatGPT and Telegram bot

telegram_bot.py

@@ -122,13 +122,23 @@ async def transcribe(self, update: Update, context: ContextTypes.DEFAULT_TYPE):
  # Transcribe the audio file
  transcript = self.openai.transcribe(filename_mp3)
 
- # Send the transcript
- await context.bot.send_message(
- chat_id=chat_id,
- reply_to_message_id=update.message.message_id,
- text=transcript,
- parse_mode=constants.ParseMode.MARKDOWN
- )
+ if self.config['voice_reply_transcript']:
+ # Send the transcript
+ await context.bot.send_message(
+ chat_id=chat_id,
+ reply_to_message_id=update.message.message_id,
+ text=f'_Transcript:_\n"{transcript}"',
+ parse_mode=constants.ParseMode.MARKDOWN
+ )
+ else:
+ # Send the response of the transcript
+ response = self.openai.get_chat_response(chat_id=chat_id, query=transcript)
+ await context.bot.send_message(
+ chat_id=chat_id,
+ reply_to_message_id=update.message.message_id,
+ text=response,
+ parse_mode=constants.ParseMode.MARKDOWN
+ )
  except Exception as e:
  logging.exception(e)
  await context.bot.send_message(