Qwen3-TTS-Flash

Will be retired on October 10, 2026View announcement

Copy success!

Add to Compare

Overview

Qwen3-TTS-Flash model is Tongyi's latest offline speech synthesis model. It boasts 51 highly expressive human-like timbres and can synthesize audio with low latency and high stability. It also supports multiple languages and dialects, and allows for multilingual output using the same timbre. Trained on massive amounts of data, the model can adaptively adjust tone based on the text and handles complex text synthesis effectively.This model is provided as a snapshot version.

Input

Text

Output

Audio

Features

Prefix Completion

Enable Partial Mode when calling the Qwen API to make the model continue strictly from your provided prefix text.View docs

Function Calling

Use function calling to connect large language models with external tools and systems.View docs

Cache

Context Cache stores shared prefixes for long-context requests to reduce repeated computation, improve latency, and lower cost.View docs

Structured Outputs

Structured Outputs help ensure the model returns a JSON string in the expected format.View docs

Batches

Asynchronously process requests in batches to reduce costs.View docs

Web Search

Enable web search so the model can answer with real-time retrieved data.View docs

Fine-tuning

Train models on sample data to better adapt them to specific tasks.View docs

Pricing

TTS
$0.1Per 10,000 characters

Rate Limits

RPMRequests Per Minute
180

API Reference

Call API

Copy success!

1234567891011121314

# The DashScope SDK must be version 1.23.1 or later
import os
import dashscope

text = "Let me recommend a T-shirt to you. This one is really super good-looking. The color is very elegant, and it is also a great item for matching. You can buy it without hesitation. It is really very good-looking and very forgiving for all body types. No matter what your body shape is, you will look great in it. I recommend you to place an order."
response = dashscope.audio.qwen_tts.SpeechSynthesizer.call(
    # Only qwen-tts models are supported. Do not use other models
    model="qwen3-tts-flash-2025-11-27",
    # If the environment variable is not set, replace it with your Model Studio API key: api_key="sk-xxx"
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    text=text,
    voice="Cherry",
)
print(response)