By No Code MBA · Facts checked
- Provider
- Qwen
- Announcement date
- Status at last check
- Generally available
- Model family
- Qwen-Audio-3.1
- Capabilities
- Audio
What changed
Qwen-Audio-3.1-TTS-Next is an audio generation model that produces speech, sound effects and ambient sound together in one pass from text, timestamps and reference audio. Alibaba lists single-speaker speech, multi-speaker dialogue, podcasts and cinematic soundscapes as supported tasks. It accepts up to 3,000 characters of text and up to three reference clips of 30 seconds each, and returns up to 120 seconds of audio, or 240 seconds for podcasts.
Access and availability
Hosted on Alibaba Cloud Model Studio via HTTPS API as qwen-audio-3.1-tts-next, in the Singapore and China (Beijing) regions, with a 180 requests per minute limit. No open weights were announced.
Official access documentationPricing
$0.93 per million input tokens and $1.87 per million output tokens (Singapore); $0.848 input and $1.696 output per million tokens (China Beijing)
Official pricingWhat you can build
Feed it a short script with dialogue and scene cues and compare the mixed audio against separate speech and effects pipelines for your project.
Limitations
Supports Chinese and English only and returns non-streaming output; Alibaba offers a separate TTS-Flash variant for real-time streaming use. Raw PCM is not accepted as reference audio.