mirror of
https://github.com/farcasclaudiu/openclaw.git
synced 2026-06-28 17:01:53 +03:00
docs: update routing/messages/session config
This commit is contained in:
+2
-7
@@ -7,7 +7,7 @@ read_when:
|
||||
# Audio / Voice Notes — 2025-12-05
|
||||
|
||||
## What works
|
||||
- **Optional transcription**: If `inbound.transcribeAudio.command` is set in `~/.clawdis/clawdis.json`, CLAWDIS will:
|
||||
- **Optional transcription**: If `routing.transcribeAudio.command` is set in `~/.clawdis/clawdis.json`, CLAWDIS will:
|
||||
1) Download inbound audio to a temp path when WhatsApp only provides a URL.
|
||||
2) Run the configured CLI (templated with `{{MediaPath}}`), expecting transcript on stdout.
|
||||
3) Replace `Body` with the transcript, set `{{Transcript}}`, and prepend the original media path plus a `Transcript:` section in the command prompt so models see both.
|
||||
@@ -18,7 +18,7 @@ read_when:
|
||||
Requires `OPENAI_API_KEY` in env and `openai` CLI installed:
|
||||
```json5
|
||||
{
|
||||
inbound: {
|
||||
routing: {
|
||||
transcribeAudio: {
|
||||
command: [
|
||||
"openai",
|
||||
@@ -32,11 +32,6 @@ Requires `OPENAI_API_KEY` in env and `openai` CLI installed:
|
||||
"text"
|
||||
],
|
||||
timeoutSeconds: 45
|
||||
},
|
||||
reply: {
|
||||
mode: "command",
|
||||
command: ["pi", "{{Body}}"],
|
||||
agent: { kind: "pi" }
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user