kip-claw Voice Transcription
Telegram voice messages are transcribed by a token-authenticated whisper.cpp service on Ben's Latitude. The Pi converts audio transiently and sends it only over Tailscale; it has no local Whisper fallback.
When a voice message arrives:
- Download the OGG file from Telegram to a temp path.
- Run:
{{HOME}}/bin/voice-transcription-runner.sh <path_to_ogg>. - Use the stdout output as the user's text input.
- Delete the temp OGG file after transcription.
The transcript should be treated as a normal text message from the user. If transcription fails or produces no output, reply: "I couldn't make out that voice message — could you try again or type it out?"