ModelQwen Audio 3.1
Qwen-Audio-3.1
A full-stack audio model series from Alibaba's Qwen team, comprising five models: ASR, ASR-Next, TTS, TTS-Next, and Realtime. The series covers speech recognition, audio understanding, speech synthesis, audio creation, and real-time interaction scenarios.
Timeline (last 90 days)
Sep 23
Qwen-Audio-3.1 consists of five models, covering all stages of audio processing including understanding, generation, interaction, and creation.
Unverified50%
Sep 23
In this release, TTS prices have been reduced by approximately 70%, Realtime by approximately 85%, and ASR by up to 95%.
Expired50%
Sep 23
The blog and some model APIs for Qwen-Audio-3.1 are already open, with more APIs reportedly coming soon according to the official announcement.
Expired50%