By No Code MBA · Facts checked
- Provider
- Qwen
- Announcement date
- Status at last check
- Generally available
- Model family
- Qwen-Audio 3.1
- Capabilities
- Audio, Text
What changed
Alibaba announced the Qwen-Audio 3.1 speech suite at Apsara 2026, covering speech recognition, text-to-speech and real-time speech-to-speech conversation. Model Studio lists ASR models in flash, streaming, message and file-transcription variants, TTS models in plus and flash tiers, qwen-audio-3.1-realtime-plus for end-to-end voice conversation, and qwen-audio-3.1-tts-next, which Alibaba says generates dialogue and ambient sound together from a script in one pass.
Access and availability
Hosted only, through Alibaba Cloud Model Studio, using model IDs such as qwen-audio-3.1-asr-flash, qwen-audio-3.1-tts-plus and qwen-audio-3.1-realtime-plus. Examples use the Singapore region, with separate API keys for Beijing.
Official access documentationWhat you can build
Wire the Realtime model into a voice agent prototype and test turn-taking and interruption handling in a noisy room before scaling it.
Limitations
No open weights were announced. Alibaba's press release gives no accuracy figures, language lists or pricing for the 3.1 models.