API docs / Audio models

qwen3-tts API

Converts text into natural-sounding speech across 10 languages including Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, and Italian. Features three modes: custom voice selection from preset speakers (Aiden, Dylan, Eric, Ono_anna, Ryan, Serena, Sohee, Uncle_fu, Vivian), voice cloning from just 3 seconds of reference audio, and voice design from natural language descriptions. Supports cross-language voice cloning, multiple Chinese dialects, style instructions for controlling emotion and speaking pace, and low-latency streaming with 97 millisecond response time. Trained on over 5 million hours of speech data and can generate over 10 minutes of continuous audio without quality degradation.

Model id
qwen/qwen3-tts
Provider
qwen
Output
Audio
Price
From 1 credits per run, the same as on voor.ai. Options such as length or resolution can change it.

Request

POST https://voor.ai/v1/generations with "model": "qwen/qwen3-tts". Poll GET /v1/tasks/{id} or receive the signed webhook. See the overview for keys, idempotency, webhooks and errors.

curl https://voor.ai/v1/generations \
  -H "Authorization: Bearer $VOOR_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
  "model": "qwen/qwen3-tts",
  "input": {
    "prompt": "A red fox standing in fresh snow at golden hour, soft light"
  },
  "callback_url": "https://example.com/webhooks/voor"
}'

# Then poll the task (or wait for the webhook):
curl https://voor.ai/v1/tasks/TASK_ID \
  -H "Authorization: Bearer $VOOR_API_KEY"

Input parameters

NameTypeDetails
promptrequiredstring

Text to synthesize into speech

reference_audiosarray of URLs

Reference audio file for voice cloning (only for 'voice_clone' mode)

Up to 1 files · Accepts audio/*

languagestring

Default: auto

One of: auto, Chinese, English, Japanese, Korean, French, German, Italian, Spanish, Portuguese, Russian

voicestring

Default: Serena

One of: Aiden, Dylan, Eric, Ono_anna, Ryan, Serena, Sohee, Uncle_fu, Vivian

modestring

Default: custom_voice

One of: custom_voice, voice_clone, voice_design

reference_textstring

Transcript of the reference audio (recommended for 'voice_clone' mode)

style_instructionstring

Optional style/emotion instruction (e.g., 'speak slowly and calmly', 'excited tone')

voice_descriptionstring

Natural language description of desired voice (only for 'voice_design' mode). Example: 'A warm, friendly female voice with a slight British accent'