server:
  host: 127.0.0.1
  port: 9881
  tts_config: GPT_SoVITS/configs/tts_infer.yaml

cors_allow_origins:
  - "*"

upload:
  dir: runtime/uploads
  min_ref_seconds: 3
  max_ref_seconds: 10
  max_upload_mb: 80

default_voice: default

defaults:
  text_lang: zh
  prompt_lang: zh
  media_type: wav
  text_split_method: cut5
  batch_size: 1
  batch_threshold: 0.75
  split_bucket: true
  speed_factor: 1.0
  fragment_interval: 0.3
  seed: -1
  parallel_infer: true
  repetition_penalty: 1.35
  sample_steps: 32
  super_sampling: false
  overlap_length: 2
  min_chunk_length: 16

emotion_presets:
  neutral: {}
  happy:
    temperature: 1.1
    top_p: 0.95
  calm:
    temperature: 0.8
    top_p: 0.85
    speed_factor: 0.92
  sad:
    temperature: 0.75
    top_p: 0.85
    speed_factor: 0.9
  angry:
    temperature: 1.2
    top_k: 20
    repetition_penalty: 1.25

voices:
  default:
    description: Replace this profile with your reference voice.
    ref_audio_path: reference.wav
    prompt_text: Replace this with the exact text spoken in reference.wav.
    prompt_lang: zh
    text_lang: zh