Qwen3 TTS is Alibaba's text to speech model. A multilingual text-to-speech model from Alibaba's Qwen team offering expressive, low-latency speech synthesis across 10 languages with 9 preset voices.
Specifications
Canonical IDalibaba-qwen3-tts
TypeText to Speech
StatusActive
CreatorAlibabaAlibaba
Providers
Input ModalitiesText
Output ModalitiesAudio

Capabilities

Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text·
Image·
Audio✓
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Pricing by Provider

US Dollar ($)
Per 1M tokens
ProviderStandard
Audio In
$ / 1K chars
Replicate logo
Replicate
replicate/qwen/qwen3-tts
$0.020

Cost Calculator

US Dollar ($)
Preset:

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Qwen Audio 3 Flash ASR————Available
Qwen Audio 3 Flash ASR Filetrans————Available
Qwen Audio 3 Flash ASR Streaming————Available
Qwen Audio 3 Flash Realtime——$0.230$0.930Available
Qwen Audio 3 Flash TTS————Available
Qwen Audio 3 Plus Realtime——$0.800$6.40Available
Qwen Audio 3 Plus TTS————Available
Qwen Audio 3.1 Flash Realtime——$0.230$0.930Available
Qwen Audio 3.1 Flash TTS——$0.230$1.87Available
Qwen Audio 3.1 Plus Realtime——$0.800$6.40Available
Qwen3 TTS————Current

Model IDs

alibaba-qwen3-tts
Qwen/Qwen3-TTS
qwen3-tts-flash
qwen3-tts-vc-realtime
replicate/qwen/qwen3-tts