michael/AI-Profile-Router
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Reuse Athena router key for OpenClaw dictation

Browse Source
This commit is contained in:
Mikei386
2026-09-16 15:28:10 +02:00
parent ba68d4e8fb
commit 8df3e1ad43
6 changed files with 50 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files
integrations/openclaw-athena-talk/README.md
+4 -2
View File
@@ -67,8 +67,10 @@ the 8 kHz G.711 audio through the Gateway. The plugin converts it to PCM WAV
and calls the same Athena `/audio/transcriptions` endpoint used by Talk. The
transcribed text is returned to the composer; this path does not invoke the
agent or TTS. The transcription provider reuses `talk.realtime.providers.athena-talk`
and the configured model provider for its URL/key, so no second credential is
needed. In `talk.catalog`, it appears under `transcription.providers`. OpenClaw
and the configured model provider for its URL/key. If that model provider has
no key, it reuses `tts.providers.openai.apiKey` only when the TTS and STT URLs
have the same origin. No second credential is needed. In `talk.catalog`, it
appears under `transcription.providers`. OpenClaw
currently gives a transcription provider five seconds to return its final text
after recording stops; the plugin caps its Whisper request at 4.5 seconds.