AlibabaQwen Audio
Qwen Audio 3.1 TTS Next
TTS Next generates speech and non-speech audio in one interface. The guide lists Chinese and English support.
Technical details
Reference audio must be at most 30 seconds and 10 MB per clip. WAV, MP3, OGG and Opus are supported; raw PCM is excluded.Qwen audio generation guide
Practical use
Practical guidance. Describe the speakers, background sound and sequence separately. Listen for timing conflicts between speech and effects before placing the result in a video or interactive scene.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | API |
| Model identifiers | qwen-audio-3.1-tts-next |
| Duration | Up to 240 seconds in podcast mode; 120 seconds in other modes.Qwen audio generation guide |
| Input | Up to 3,000 text characters and three reference clips.Qwen audio generation guide |
Related models
- Qwen Audio 3.1 Realtime
Alibaba · Qwen Audio
Full-duplex speech and text model family with Plus and Flash variants and acoustic, semantic and manual turn controls.
Launch date not confirmedAPI - Qwen Audio 3.1 TTS
Alibaba · Qwen Audio
Text-to-speech family with Plus for detailed voice performance and Flash for low-latency interaction.
Launch date not confirmedAPI