telegram-voice-transcribe

Transcribe Telegram voice notes into text via OpenAI Whisper (whisper-1).

Quick Workflow

1. Detect a voice message: look for voice.file_id or audio.file_id in the inbound message metadata.
2. Run the transcription script:

   python3 ~/openclaw/skills/telegram-voice-transcribe/scripts/transcribe.py \
     --file-id <file_id> --language es
   

3. Read the JSON output — transcript field contains the text.
4. Respond to the user based on the transcript content (treat it like typed text).

Script Modes