voice_models.yaml

# Voice model presets for EchoCoach (ASR + TTS).
# Override defaults via ECHOCOACH_ASR_PRESET / ECHOCOACH_TTS_PRESET in .env

defaults:
  asr_preset: whisper-cpp-base
  tts_preset: piper-multilingual
  # Realtime streaming TTS for TeacherVoice VoiceOut (set ECHOCOACH_TTS_PRESET to match)
  realtime_tts_preset: vibevoice-realtime-0.5b
  coach_model: minicpm5-1b-language-lesson-hub
  coach_fallbacks:
    - minicpm5-1b-language-lesson-lora
    - minicpm5-1b
  max_seconds: 30

languages:
  - code: en
    label: English
  - code: fr
    label: French
  - code: de
    label: German
  - code: es
    label: Spanish
  - code: it
    label: Italian
  - code: pt
    label: Portuguese
  - code: nl
    label: Dutch
  - code: pl
    label: Polish
  - code: el
    label: Greek
  - code: ar
    label: Arabic
  - code: ja
    label: Japanese
  - code: zh
    label: Chinese (Mandarin)
  - code: vi
    label: Vietnamese
  - code: ko
    label: Korean

asr:
  cohere-transcribe:
    label: Cohere Transcribe 2B (14 languages)
    backend: cohere
    model_id: CohereLabs/cohere-transcribe-03-2026

  whisper-cpp-tiny:
    label: Whisper.cpp tiny (CPU, fast)
    backend: whisper_cpp
    model_size: tiny

  whisper-cpp-base:
    label: Whisper.cpp base (CPU, better WER)
    backend: whisper_cpp
    model_size: base

# Optional omni speech-in/speech-out (GPU; set ECHOCOACH_VOICE_PROFILE=omni)
omni:
  minicpm-o-4.5:
    label: MiniCPM-o 4.5 (GPU omni — falls back to pipeline until wired)
    model_id: openbmb/MiniCPM-o-4_5
    languages: [en, zh]

tts:
  piper-multilingual:
    label: Piper TTS (local VoiceOut)
    backend: piper
    voices:
      en: en_US-lessac-medium
      fr: fr_FR-siwis-medium
      de: de_DE-thorsten-medium
      es: es_ES-sharvard-medium
      it: it_IT-riccardo-medium
      pt: pt_BR-faber-medium
      nl: nl_NL-mls-medium
      pl: pl_PL-darkman-medium
      el: el_GR-rapunzelina-low
      ar: ar_JO-kareem-medium
      ja: ja_JP-natsuki-medium
      zh: zh_CN-huayan-medium
      vi: vi_VN-25hours-single
      ko: ko_KR-kss-medium
    fallback_voice: en_US-lessac-medium

  # Microsoft VibeVoice Realtime — streaming TTS, ~300ms to first audio (GPU recommended).
  # https://huggingface.co/microsoft/VibeVoice-Realtime-0.5B
  # English-first; also supports de, fr, it, es, pt, nl, pl, ja, ko (experimental).
  # Requires transformers + torch; falls back to Piper until fully wired in echocoach.
  vibevoice-realtime-0.5b:
    label: VibeVoice Realtime 0.5B (streaming, ~300ms)
    backend: vibevoice
    model_id: microsoft/VibeVoice-Realtime-0.5B
    streaming: true
    realtime: true
    languages: [en, de, fr, it, es, pt, nl, pl, ja, ko]
    fallback_language: en