feat(desktop,docs): surface stt.echo_transcripts in desktop settings and docs

Adapted from PR #53038 (stt.echo) to the stt.echo_transcripts key:
- desktop Voice settings section gains the Echo Transcripts toggle with
  label + description copy
- configuration.md documents stt.enabled / stt.echo_transcripts
This commit is contained in:
Kong 2026-07-05 05:47:36 -07:00 committed by Teknium
parent 4be749d151
commit 558001307a
2 changed files with 7 additions and 0 deletions

View file

@ -335,6 +335,7 @@ export const FIELD_LABELS: Record<string, string> = defineFieldCopy({
},
stt: {
enabled: 'Speech To Text',
echoTranscripts: 'Echo Transcripts',
provider: 'Speech-To-Text Provider',
local: {
model: 'Local Transcription Model',
@ -486,6 +487,7 @@ export const FIELD_DESCRIPTIONS: Record<string, string> = defineFieldCopy({
},
stt: {
enabled: 'Enable local or provider-backed speech transcription.',
echoTranscripts: 'Post the raw 🎙️ transcript of voice messages back to the chat.',
elevenlabs: {
languageCode: 'Optional ISO-639-3 language code. Blank lets ElevenLabs auto-detect.'
}
@ -568,6 +570,7 @@ export const SECTIONS: DesktopConfigSection[] = [
keys: [
'tts.provider',
'stt.enabled',
'stt.echo_transcripts',
'stt.provider',
'voice.auto_tts',
'tts.edge.voice',

View file

@ -1543,6 +1543,8 @@ Hashes are deterministic — the same user always maps to the same hash, so the
```yaml
stt:
enabled: true # Auto-transcribe inbound voice messages (default: true)
echo_transcripts: true # Post raw transcripts back to the chat as 🎙️ "..." (default: true)
provider: "local" # "local" | "groq" | "openai" | "mistral"
local:
model: "base" # tiny, base, small, medium, large-v3
@ -1551,6 +1553,8 @@ stt:
# model: "whisper-1" # Legacy fallback key still respected
```
Set `stt.echo_transcripts: false` when the gateway should transcribe voice notes for the agent but must not post the raw transcript back to the chat (for example, customer-facing WhatsApp bots).
Provider behavior:
- `local` uses `faster-whisper` running on your machine. Install it separately with `pip install faster-whisper`.