serrrfiratandClaude Opus 4.6 bbb2d5c4dd feat: add audio transcription pipeline with OpenAI Whisper and Telegram voice notes (#90) ...

Adds speech-to-text support so WASM channels can emit audio attachments
that get automatically transcribed before reaching the agent. Telegram
voice notes are the first integration — downloaded via Bot API and
transcribed via OpenAI Whisper.

- Extend WIT with attachment-kind, attachment records on emitted-message
- Add Attachment/AttachmentKind types to channel.rs and IncomingMessage
- Add TranscriptionProvider trait, AudioFormat enum, TranscriptionMiddleware
- Implement OpenAI Whisper provider (multipart POST, 25MB limit)
- Add TranscriptionConfig + TranscriptionSettings with env var overrides
- Parse Telegram voice messages, download via getFile, emit as attachments
- Apply transcription in both process/dispatch emitted message paths
- Graceful degradation: download failures show "[Voice note: download failed]"
- Validate attachment sizes (10MB max), drop oversized without losing message

Co-Authored-By: Claude Opus 4.6 <[email protected]>

2026-02-21 14:56:08 +04:00

..

channel.wit

feat: add audio transcription pipeline with OpenAI Whisper and Telegram voice notes (#90)

2026-02-21 14:56:08 +04:00

tool.wit

feat: Sandbox jobs (#4)

2026-02-11 08:31:25 +00:00