github/openclaw
1
1
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-02-19 18:39:20 -05:00
Code Issues Packages Projects Releases Wiki Activity

docs: clarify transcript prompt and config

Browse Source
This commit is contained in:
Peter Steinberger
2025-11-25 23:14:23 +01:00
parent e642f128ae
commit 5dced02a20
3 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
CHANGELOG.md
View File

@@ -4,7 +4,7 @@
### Pending
- Web auto-replies now resize/recompress media and honor `inbound.reply.mediaMaxMb` in `~/.warelay/warelay.json` (default 5 MB) to avoid provider/API limits.
- Optional voice-note transcription: set `inbound.transcribeAudio.command` (e.g., OpenAI Whisper CLI) to turn inbound audio into text before templating/Claude; verbose logs surface when transcription runs.
- Optional voice-note transcription: set `inbound.transcribeAudio.command` (e.g., OpenAI Whisper CLI) to turn inbound audio into text before templating/Claude; verbose logs surface when transcription runs. Prompts now include the original media path plus a `Transcript:` block so models see both.
## 1.0.4 — 2025-11-25

2
README.md
View File

@@ -75,7 +75,7 @@ Install from npm (global): `npm install -g warelay` (Node 22+). Then choose **on
}
}
```
- Works for Web and Twilio providers; verbose mode logs when transcription runs. If transcription fails, the original Body is used.
- Works for Web and Twilio providers; verbose mode logs when transcription runs. The command prompt includes the original media path plus a `Transcript:` block so models see both. If transcription fails, the original Body is used.
## Providers
- **Twilio (default):** needs `.env` creds + WhatsApp-enabled number; supports delivery tracking, polling, webhooks, and auto-reply typing indicators.

2
docs/claude-config.md
View File

@@ -59,7 +59,7 @@ Notes on this configuration:
- Host local paths for Twilio using the media server/Tailscale Funnel.
- Send buffers directly for the Web provider.
- Inbound media is downloaded (≤5 MB) and exposed to your templates as `{{MediaPath}}`, `{{MediaUrl}}`, and `{{MediaType}}`. You can mention this in your prompt if you want Claude to reason about the attachment. Outbound media from Claude (via `MEDIA:`) is resized/recompressed on the Web provider path; control the cap with `inbound.reply.mediaMaxMb` (default 5).
- Voice notes: set `inbound.transcribeAudio.command` to run a CLI that emits the transcript to stdout (e.g., OpenAI Whisper: `openai api audio.transcriptions.create -m whisper-1 -f {{MediaPath}} --response-format text`). If it succeeds, warelay replaces `Body` with the transcript before invoking Claude.
- Voice notes: set `inbound.transcribeAudio.command` to run a CLI that emits the transcript to stdout (e.g., OpenAI Whisper: `openai api audio.transcriptions.create -m whisper-1 -f {{MediaPath}} --response-format text`). If it succeeds, warelay replaces `Body` with the transcript and adds the original media path plus a `Transcript:` block into the prompt before invoking Claude.
## Testing the setup
1. Start a relay (auto-selects Web when logged in, otherwise Twilio polling):