vrr/openclaw
2
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-04-28 06:31:11 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 14

fix(feishu): transcribe inbound voice notes

Browse source
This commit is contained in:
Peter Steinberger 2026-04-26 04:47:33 +01:00
parent 38e61e0046
commit 29741f696a
No known key found for this signature in database
7 changed files with 206 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

9
docs/channels/feishu.md
View file

@ -414,6 +414,15 @@ Full configuration: [Gateway configuration](/gateway/configuration)
- ✅ Video/media
- ✅ Stickers
Inbound Feishu/Lark audio messages are normalized as media placeholders instead
of raw `file_key` JSON. When `tools.media.audio` is configured, OpenClaw
downloads the voice-note resource and runs shared audio transcription before the
agent turn, so the agent receives the spoken transcript. If Feishu includes
transcript text directly in the audio payload, that text is used without another
ASR call. Without an audio transcription provider, the agent still receives a
`<media:audio>` placeholder plus the saved attachment, not the raw Feishu
resource payload.
### Send
- ✅ Text