# Qwen3 TTS

> Alibaba's unified TTS with three modes: preset speakers (custom_voice), instant voice cloning from reference audio (voice_clone), and voice creation from a text description (voice_design).

- **Provider**: replicate
- **Model ID**: qwen/qwen3-tts
- **Category**: tts_voice
- **Credits**: 47 per request
- **Pricing Type**: token_based

## API Endpoint

Base URL: https://api.core.today/v1

### Create Prediction
POST /predictions

### Get Status
GET /predictions/{job_id}

### Cancel
DELETE /predictions/{job_id}

## Authentication

Header: `X-API-Key: YOUR_API_KEY`

## Input Parameters

- `style_instruction` (string, optional): Optional style/emotion instruction (e.g., 'speak slowly and calmly', 'excited tone')
- `reference_audio` (string, optional): Reference audio file for voice cloning (only for 'voice_clone' mode)
- `language` (string, optional): Language of the text (use 'auto' for automatic detection) (Default: `auto`; Options: `auto`, `Chinese`, `English`, `Japanese`, `Korean`, `French`, `German`, `Italian`, `Spanish`, `Portuguese`, `Russian`)
- `speaker` (string, optional): Preset speaker voice (only for 'custom_voice' mode) (Default: `Serena`; Options: `Aiden`, `Dylan`, `Eric`, `Ono_anna`, `Ryan`, `Serena`, `Sohee`, `Uncle_fu`, `Vivian`)
- `mode` (string, optional): TTS mode: 'custom_voice' uses preset speakers, 'voice_clone' clones from reference audio, 'voice_design' creates voice from description (Default: `custom_voice`; Options: `custom_voice`, `voice_clone`, `voice_design`)
- `voice_description` (string, optional): Natural language description of desired voice (only for 'voice_design' mode). Example: 'A warm, friendly female voice with a slight British accent'
- `reference_text` (string, optional): Transcript of the reference audio (recommended for 'voice_clone' mode)
- `text` (string, **required**): Text to synthesize into speech

## Example Request

```json
{
  "model": "qwen/qwen3-tts",
  "input": {
    "mode": "custom_voice",
    "language": "auto",
    "text": "Hello, I'm Aiden and it's very nice to meet you",
    "speaker": "Aiden"
  }
}
```

## Response Format

```json
{
  "job_id": "abc123",
  "status": "pending",
  "provider": "replicate",
  "model": "black-forest-labs/flux-schnell",
  "created_at": "2026-01-01T00:00:00Z",
  "result": null,
  "error": null
}
```

Status values: `pending`, `processing`, `completed`, `failed`, `cancelled`

## Usage Flow

1. POST /predictions with model and input → receive job_id
2. Poll GET /predictions/{job_id} until status is `completed` or `failed`
3. Result contains output URL(s) or data

## Output Type

url

## Tags

text-to-speech, tts, audio, voice-synthesis, voice-cloning, voice-design, qwen, multilingual

## Documentation

https://replicate.com/qwen/qwen3-tts


## Token Pricing

- Input: 0.0465 credits/token
- Output: 0.0465 credits/token