> ## Documentation Index
> Fetch the complete documentation index at: https://docs.crun.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Qwen3 TTS Speech Synthesis API
> Qwen's speech synthesis model delivers human-like voices with natural expressiveness. It supports multiple languages and dialects, generates multilingual content using a single voice, and automatically adapts tone to handle complex text.
## Overview
Qwen3-TTS is a text-to-speech model from the Qwen team at Alibaba Cloud. This model turns text into natural-sounding
speech across 10 languages, including Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish,
and Italian.\
Includes three powerful modes: Voice, Clone, and Design.
#### What you can do with it
#### Speech Synthesis:
Enter the text to be synthesized, select the built-in voice of the system, and the speech can be generated.
Multi-language mixed input is supported.
#### Voice Cloning:
Give the model 3 seconds of audio and it can reproduce that voice speaking any text you provide. The cloning works
across languages too—clone a voice in English and use it to speak Chinese.
#### Design Voice:
Describe the voice you want in plain language and the model creates it. You might ask for “a warm
storyteller voice with gentle pacing” or “a deep male voice with a British accent.” The model interprets your
description and generates matching speech.
#### Control speech style:
Use natural language instructions to adjust how the speech sounds. You can control emotion, speaking speed, and tone.
The model adapts its output based on the meaning of your text, placing pauses naturally and emphasizing the right words.
## Query Task Status
After submitting a task, use the unified query endpoint to check progress and retrieve results:
Learn how to query task status and retrieve generation results
For production use, we recommend using the `callback_url` parameter to receive automatic notifications when generation completes, rather than polling the status endpoint.
## Related Resources
Explore all available models
Check credits and account usage
## OpenAPI
````yaml models/qwen/qwen-tts.json post /api/v1/client/job/CreateTask
openapi: 3.0.0
info:
title: Crun Qwen TTS API
description: crun.ai Qwen3 TTS API Documentation
version: 1.0.0
contact:
name: Technical Support
email: support@crun.ai
servers:
- url: https://api.crun.ai
description: API Server
security:
- ApiKeyAuth: []
paths:
/api/v1/client/job/CreateTask:
post:
summary: qwen3 tts speech synthesis
operationId: qwen3-tts-speech-synthesis
requestBody:
required: true
content:
application/json:
schema:
type: object
required:
- model
- input
properties:
model:
type: string
enum:
- qwen3-tts/speech-synthesis
description: |-
The model name to use for generation. Required field.
- Must be `qwen3-tts/speech-synthesis` for this endpoint
callback_url:
type: string
format: uri
description: >-
Optional. Callback URL for receiving task completion
notifications.
- System will POST task status and results to this URL when
generation completes
- Callback payloads structure is consistent with the `data`
object returned by the task status query
- Your callback endpoint should accept POST requests with
JSON payload containing results
- It returns an HTTP 200 status code upon successful receipt
example: https://your-domain.com/api/callback
input:
type: object
description: Input parameters for the Qwen3 TTS speech synthesis task
required:
- text
- voice
properties:
text:
type: string
description: >-
The text to synthesize. Mixed-language input is
supported.
minLength: 1
maxLength: 600
example: >-
The weather is lovely today. Let's take a walk in the
park.
voice:
type: string
description: >-
the voice to use. See [Supported system
voices](https://www.alibabacloud.com/help/en/model-studio/qwen-tts#bac280ddf5a1u).
minLength: 1
maxLength: 600
example: Cherry
language_type:
type: string
enum:
- Auto
- Chinese
- English
- German
- Italian
- Portuguese
- Spanish
- Japanese
- Korean
- French
description: >-
Language type for synthesis. Use `Auto` to let the
system detect language.
- Use this when the text language is uncertain or
contains multiple languages. The model automatically
matches pronunciation for different language segments in
the text, but cannot guarantee perfectly accurate
pronunciation.
- Specify language: Use this when the text is in a
single language. Specifying the exact language
significantly improves synthesis quality, usually
outperforming `Auto`. Supported values include the
following:
default: Auto
example: Chinese
instructions:
type: string
description: >-
Optional. Style or delivery instructions, such as tone,
emotion, or speaking style. Only Chinese and English are
supported.
maxLength: 1600
example: Use a warm, friendly tone and a slightly slower pace.
optimize_instructions:
type: boolean
description: >-
Optimize the `instructions` to improve the naturalness
and expressiveness of speech synthesis.
default: false
example: true
example:
model: qwen3-tts/speech-synthesis
callback_url: https://your-domain.com/api/callback
input:
text: >-
Welcome to Qwen3 TTS. We can synthesize natural speech in
multiple languages.
voice: Serena
language_type: English
instructions: Speak clearly with a friendly, confident tone.
optimize_instructions: true
responses:
'200':
description: Request successful
content:
application/json:
schema:
allOf:
- $ref: '#/components/schemas/ApiResponse'
- type: object
properties:
data:
type: object
properties:
task_id:
type: string
description: >-
Task ID, can be used with Get Task Details
endpoint to query task status
example: task_12345678
example:
code: 200
message: success
data:
task_id: task_12345678
'422':
description: Validation Error
content:
application/json:
schema:
allOf:
- $ref: '#/components/schemas/ApiResponse'
- type: object
properties:
errors:
type: array
description: Detailed validation error messages
items:
type: string
example:
- specific error field message
example:
code: 422
message: Missing Params or Type Error
errors:
- specific error field message
'500':
$ref: '#/components/responses/Error'
components:
schemas:
ApiResponse:
type: object
properties:
code:
type: integer
enum:
- 200
- 401
- 402
- 404
- 422
- 429
- 455
- 500
- 501
- 505
description: >-
Response status code
- **200**: Success - Request has been processed successfully
- **401**: Unauthorized - Authentication credentials are missing or
invalid
- **402**: Insufficient Credits - Account does not have enough
credits to perform the operation
- **404**: Not Found - The requested resource or endpoint does not
exist
- **422**: Validation Error - The request parameters failed
validation checks
- **429**: Rate Limited - Request limit has been exceeded for this
resource
- **455**: Service Unavailable - System is currently undergoing
maintenance
- **500**: Server Error - An unexpected error occurred while
processing the request
- **501**: Generation Failed - Content generation task failed
- **505**: Feature Disabled - The requested feature is currently
disabled
message:
type: string
description: Response message, error description when failed
example: success
responses:
Error:
description: Server Error
securitySchemes:
ApiKeyAuth:
type: apiKey
in: header
name: x-api-key
description: >-
All APIs require authentication via API Key.
Get API Key:
1. Visit [API Key Management Page](https://crun.ai/user-api-key) to get
your API Key
Usage:
Add to request header:
x-api-key: YOUR_API_KEY
Note:
- Keep your API Key secure and do not share it with others
- If you suspect your API Key has been compromised, reset it immediately
in the management page
````