marketing-shibata50/multica
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

docs(skills): update whisper skill with correct transcription priority

Browse source 
Clarify that local whisper is the primary provider (free, offline),
OpenAI API is the fallback, and the skill only activates when both
are unavailable. Add setup instructions noting no restart is required.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Naiyuan Qing 2026-02-09 18:13:47 +08:00
parent 1bd25c5aec
commit 7b885673da
2 changed files with 24 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

29
skills/whisper/SKILL.md
View file

@ -1,7 +1,7 @@
---
name: Audio Transcription
description: Transcribe audio files using local Whisper CLI (fallback when API is unavailable)
version: 1.0.0
description: Transcribe audio files using local Whisper CLI when automatic pre-processing is unavailable
version: 1.1.0
metadata:
emoji: "🎙️"
requires:
@ -23,14 +23,33 @@ userInvocable: false
disableModelInvocation: false
---
## Audio Transcription (Local Fallback)
## Audio Transcription (Agent Fallback)
Voice messages from channels are normally transcribed automatically via the OpenAI Whisper API before reaching you. This skill is only needed when the API is unavailable.
Voice messages from channels are pre-processed before reaching you. The transcription
priority is:
If you receive `[audio message received]` with a `File:` path (instead of `[Voice Message]` with a transcript), it means the API transcription was not available. Use local whisper to transcribe:
1. **Local whisper CLI** (free, offline) — requires `whisper` or `whisper-cli` in PATH
2. **OpenAI Whisper API** — requires an OpenAI API key in credentials
3. **No provider available** — you receive a raw file path instead of a transcript
When both providers are unavailable, you will receive `[audio message received]` with a
`File:` path instead of `[Voice Message]` with a transcript. Use local whisper to
transcribe manually:
```
whisper "<file_path>" --model base --output_format txt --output_dir /tmp
```
Then read the `.txt` file from `/tmp/` and respond based on the transcribed content.
### Setup
To enable automatic local transcription (recommended):
```bash
brew install openai-whisper
```
The first run will download the `base` model (~139MB) to `~/.cache/whisper/`.
No app restart is required — the binary is detected automatically on the next
voice message.

2
src/channels/manager.ts
View file

@ -265,8 +265,6 @@ export class ChannelManager {
// Keep heartbeat acknowledgements internal (same behavior as desktop/gateway stream path).
if (isHeartbeatAckEvent(event)) {
if (event.type === "message_end") {
this.stopTyping();
this.removeAckReaction();
this.aggregator = null;
}
return;