jb/paseo
1
0
Fork 0
Code Issues 1 Pull Requests Actions Packages Projects Releases Wiki Activity

Configure STT language from settings (#941)

Browse Source 
* Configure STT language from settings

* Update websocket speech mock for language config
This commit is contained in:
Mohamed Boudra
2026-05-12 15:03:53 +08:00
committed by GitHub
parent 417abed6a5
commit 1a8fdcd388
20 changed files with 411 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files
public-docs/configuration.md
+1
View File
@@ -161,6 +161,7 @@ In the mobile app, enter the password in the direct connection setup screen.
- `PASEO_LOCAL_MODELS_DIR`, control local model directory
- `PASEO_DICTATION_LOCAL_STT_MODEL`, override local dictation STT model
- `PASEO_VOICE_LOCAL_STT_MODEL`, `PASEO_VOICE_LOCAL_TTS_MODEL`, override local voice STT/TTS models
- `PASEO_DICTATION_LANGUAGE`, `PASEO_VOICE_LANGUAGE`, override dictation and voice STT language
- `PASEO_VOICE_LOCAL_TTS_SPEAKER_ID`, `PASEO_VOICE_LOCAL_TTS_SPEED`, optional local voice TTS tuning
## Schema
public-docs/voice.md
+9 -3
View File
@@ -24,7 +24,7 @@ This keeps credentials and execution in your environment and avoids introducing
## Local Speech
Local speech defaults to model IDs `parakeet-tdt-0.6b-v3-int8` (STT) and `kokoro-en-v0_19` (TTS, speaker 0 / voice 00).
Local speech defaults to model IDs `parakeet-tdt-0.6b-v3-int8` (STT) and `kokoro-en-v0_19` (TTS, speaker 0 / voice 00). STT language defaults to `en`.
Missing models are downloaded at daemon startup into `$PASEO_HOME/models/local-speech`. Downloads happen only for missing files.
@@ -32,10 +32,12 @@ Missing models are downloaded at daemon startup into `$PASEO_HOME/models/local-s
{
"version": 1,
"features": {
"dictation": { "stt": { "provider": "local", "model": "parakeet-tdt-0.6b-v3-int8" } },
"dictation": {
"stt": { "provider": "local", "model": "parakeet-tdt-0.6b-v3-int8", "language": "en" }
},
"voiceMode": {
"llm": { "provider": "claude", "model": "haiku" },
"stt": { "provider": "local", "model": "parakeet-tdt-0.6b-v3-int8" },
"stt": { "provider": "local", "model": "parakeet-tdt-0.6b-v3-int8", "language": "en" },
"tts": { "provider": "local", "model": "kokoro-en-v0_19", "speakerId": 0 }
}
},
@@ -47,6 +49,8 @@ Missing models are downloaded at daemon startup into `$PASEO_HOME/models/local-s
}
```
Set `features.dictation.stt.language` for dictation and `features.voiceMode.stt.language` for realtime voice. If voice language is omitted, Paseo uses the dictation language before falling back to `en`.
## OpenAI Speech Option
You can switch dictation, voice STT, and voice TTS to OpenAI by setting provider fields to `openai` and providing `OPENAI_API_KEY`.
@@ -74,6 +78,8 @@ You can switch dictation, voice STT, and voice TTS to OpenAI by setting provider
- `PASEO_LOCAL_MODELS_DIR`, local model storage directory
- `PASEO_DICTATION_LOCAL_STT_MODEL`, local dictation STT model ID
- `PASEO_VOICE_LOCAL_STT_MODEL`, `PASEO_VOICE_LOCAL_TTS_MODEL`, local voice STT/TTS model IDs
- `PASEO_DICTATION_LANGUAGE`, dictation STT language
- `PASEO_VOICE_LANGUAGE`, realtime voice STT language; falls back to `PASEO_DICTATION_LANGUAGE` when unset
- `PASEO_VOICE_LOCAL_TTS_SPEAKER_ID`, `PASEO_VOICE_LOCAL_TTS_SPEED`, optional local voice TTS tuning
## Operational Notes