Qwen3-TTS
Studio
Voice Synthesis · Three Modes · Qwen / Alibaba
API Endpoint
Custom Voice
Voice Design
Voice Clone
Text to Synthesize
Hello, this is Qwen three TTS running on Modal.
Speaker
Aiden
Dylan
Eric
Ono_anna
Ryan
Serena
Sohee
Uncle_fu
Vivian
Language
Auto
English
Chinese
Japanese
Korean
French
German
Spanish
Portuguese
Russian
Style Instruction
optional
Generate Speech
Text to Synthesize
It's in the top drawer… wait, it's empty? No way, that's impossible!
Voice Description
Speak in an incredulous tone, with a hint of panic creeping into your voice.
Language
Auto
English
Chinese
Japanese
Korean
French
German
Spanish
Design Voice
Reference Audio
~10 seconds, clear speech
♪
Drop audio file or click to browse
Reference Transcript
what is spoken in the reference audio
Target Text
Hello, this is a voice clone test using Qwen three TTS.
Language
Auto
English
Chinese
Japanese
Korean
X-vector only mode
Faster · no transcript needed · lower quality
Clone & Generate
Output
▶
0:00 / 0:00
↓ Download WAV