Add Parakeet v3 local STT model for multilingual dictation

v2 is English-only; v3 covers 25 European languages with automatic
language detection. The archive shares v2's filenames, architecture,
sample rate, and feature dim, so no runtime loader changes are needed.

Document that the `language` config field and PASEO_*_LANGUAGE vars
only steer the OpenAI STT provider — the local Parakeet models ignore
them, so multilingual local dictation means selecting the v3 model.

packages/server/src/server/speech/providers/local/sherpa/model-catalog.ts

@@ -23,6 +23,15 @@ export const SHERPA_ONNX_MODEL_CATALOG = {
     description: "NVIDIA Parakeet TDT v2 (offline NeMo transducer, English).",
     defaultFor: "stt",
   },
+  "parakeet-tdt-0.6b-v3-int8": {
+    kind: "stt-offline",
+    archiveUrl:
+      "https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-nemo-parakeet-tdt-0.6b-v3-int8.tar.bz2",
+    extractedDir: "sherpa-onnx-nemo-parakeet-tdt-0.6b-v3-int8",
+    requiredFiles: ["encoder.int8.onnx", "decoder.int8.onnx", "joiner.int8.onnx", "tokens.txt"],
+    description:
+      "NVIDIA Parakeet TDT v3 (offline NeMo transducer, 25 European languages, auto-detected).",
+  },
   "kokoro-en-v0_19": {
     kind: "tts",
     archiveUrl:

public-docs/voice.md

@@ -24,10 +24,19 @@ This keeps credentials and execution in your environment and avoids introducing
 
 ## Local Speech
 
-Local speech defaults to model IDs `parakeet-tdt-0.6b-v2-int8` (STT) and `kokoro-en-v0_19` (TTS, speaker 0 / voice 00). STT language defaults to `en`.
+Local speech defaults to model IDs `parakeet-tdt-0.6b-v2-int8` (STT) and `kokoro-en-v0_19` (TTS, speaker 0 / voice 00).
 
 Missing models are downloaded at daemon startup into `$PASEO_HOME/models/local-speech`. Downloads happen only for missing files.
 
+### Local STT models and language support
+
+| Model ID                    | Languages                                                                                                                                                                                                                                                                    |
+| --------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `parakeet-tdt-0.6b-v2-int8` | English only (default). Includes punctuation and capitalization.                                                                                                                                                                                                             |
+| `parakeet-tdt-0.6b-v3-int8` | 25 European languages, auto-detected: Bulgarian, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, German, Greek, Hungarian, Italian, Latvian, Lithuanian, Maltese, Polish, Portuguese, Romanian, Russian, Slovak, Slovenian, Spanish, Swedish, Ukrainian. |
+
+**To use a non-English language, switch the local STT model to `parakeet-tdt-0.6b-v3-int8`.** v3 detects the spoken language automatically — there is no per-language setting for it. The `language` field below does **not** steer the local Parakeet model (v2 is English-only, v3 auto-detects); it only applies to the OpenAI STT provider.
+
 ```json
 {
   "version": 1,
@@ -49,7 +58,20 @@ 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`.
+For multilingual local dictation, set the model to v3 — it auto-detects the language, so no `language` field is needed:
+
+```json
+{
+  "version": 1,
+  "features": {
+    "dictation": {
+      "stt": { "provider": "local", "model": "parakeet-tdt-0.6b-v3-int8" }
+    }
+  }
+}
+```
+
+The `language` field applies only to the OpenAI STT provider: 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`. It has no effect on the local Parakeet models.
 
 ## OpenAI Speech Option
 
@@ -78,8 +100,8 @@ 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_DICTATION_LANGUAGE`, dictation STT language (OpenAI STT only; ignored by local Parakeet)
-- `PASEO_VOICE_LANGUAGE`, realtime voice STT language; falls back to `PASEO_DICTATION_LANGUAGE` when unset
+- `PASEO_VOICE_LANGUAGE`, realtime voice STT language; falls back to `PASEO_DICTATION_LANGUAGE` when unset (OpenAI STT only; ignored by local Parakeet)
 - `PASEO_VOICE_LOCAL_TTS_SPEAKER_ID`, `PASEO_VOICE_LOCAL_TTS_SPEED`, optional local voice TTS tuning
 
 ## Operational Notes