ClavueClavue
AI platform · IDE · agents · models

Broadcast TTS

clavue-tts on api.clavue.com is broadcast TTS only (Uncle_Fu / Vivian / Serena, news-desk diction). Audiobook acted voices (10 speakers, pinned instructions) use the cluster gateway — same API key often works on https://ttkk.inping.com/v1. See https://ttkk.inping.com/docs/tts.html. Songs use clavue-music.

How to generate

  • POST /v1/audio/speech with model=clavue-tts
  • input = the script to read (plain text, not lyrics tags)
  • voice = Uncle_Fu (default, steady male) or Vivian (crisp female)
  • instructions = locked news-desk diction (send it; the API fills the default if omitted)
  • Timeout 120s is enough. Do not send audio_duration, seed, or reference_audio
curl -sS https://api.clavue.com/v1/audio/speech \
  -H "Authorization: Bearer $CLAVUE_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "model":"clavue-tts",
    "input":"晚间天气。城区有短时阵雨，气温二十二到二十六度。请携带雨具。",
    "voice":"Uncle_Fu",
    "instructions":"请用新闻播音腔，吐字清楚，语速中等，数字读完整，专名不吞字。不要口语，不要气声，不要唱歌。",
    "response_format":"wav"
  }' --output news.wav --max-time 120

Recommended settings

Lock the voice and the diction. Do not scan voices. Casual Bot UI speech can stay on the internal short TTS path — this product is for news desk and scripted reads.

  • voice: Uncle_Fu (default) · Vivian · Serena
  • instructions: news-desk lock (see curl). Do not write song captions here
  • response_format: wav · read the real WAV duration
{
  "model": "clavue-tts",
  "voice": "Uncle_Fu",
  "response_format": "wav"
}

Mix with music

Dialogue is clavue-tts. Beds and opening stings are clavue-music with Instrumental, no vocals. Two calls, then mix in your product. Do not ask the song model to sing the news.

Audiobook / acted voices

Long-form novel narration with jp-m-versatile, novel-f-acted, etc. is not this broadcast product. Use POST /v1/audio/speech on https://ttkk.inping.com (or ttqq with the same model ids). Full voice list and instructions template: https://ttkk.inping.com/docs/tts.html. Do not send jp-* voices to api.clavue.com clavue-tts — they collapse to Uncle_Fu.

  • Cluster release (2026-10): clavue-tts-r6-wave3-20261003
  • Default model id: clavue-tts; high-volume grouping: clavue-tts-fn / qwen3-tts-acted-ml / clavue-tts-rest
  • Whisper ASMR: clavue-asmr — https://ttkk.inping.com/docs/asmr.html

Limits

One infer per replica. Timeout 120s. Clone fields are rejected. This is not a singing model and not a replacement for clavue-music.

Do not send reference_audio. Do not send a news script to clavue-music.

Next