# Universal TTS benchmark model registry.
# Maps HuggingFace model ID → supported tasks + per-task extra body fields.
# To add a new TTS model: add an entry here. No code changes required.
#
# The server auto-loads its Deploy YAML from vllm_omni/deploy/<model>.yaml via
# the Pipeline + Deploy schema introduced in #2383, so no stage_config path
# is tracked here.

models:
  # -CustomVoice checkpoints lack speaker_encoder weights, so voice_clone is
  # NOT supported (an attempt raises ValueError from _extract_speaker_embedding
  # at model runtime).  Use -Base for voice_clone.
  Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice:
    supported_tasks: [default_voice, voice_design]
    backend: openai-audio-speech
    endpoint: /v1/audio/speech
    task_extra_body:
      default_voice:
        voice: Vivian
        language: English
        task_type: CustomVoice
      voice_design:
        task_type: VoiceDesign
        language: English

  Qwen/Qwen3-TTS-12Hz-1.7B-Base:
    supported_tasks: [voice_clone]
    backend: openai-audio-speech
    endpoint: /v1/audio/speech
    task_extra_body:
      voice_clone:
        task_type: Base

  openbmb/VoxCPM2:
    supported_tasks: [voice_clone, default_voice]
    trust_remote_code: true
    backend: openai-audio-speech
    endpoint: /v1/audio/speech
    task_extra_body:
      voice_clone: {}
      default_voice:
        voice: default