Alibaba releases Qwen-Audio-3.1 lineup and cuts audio AI prices
Alibaba’s Qwen team has released Qwen-Audio-3.1, a five-model lineup covering automatic speech recognition, text-to-speech and real-time interaction. The ASR model is designed to improve recognition across languages and dialects while removing filler words and repeated phrases. ASR-Next adds speaker identification with timestamps and can detect emotions, ambient sounds and machine noise.
The text-to-speech models support multilingual generation and cross-language voice transfer. Users can specify a voice’s emotion, speed and style with text prompts. TTS-Next combines a language model with diffusion technology to produce speech, sound effects and background audio in one pass. The real-time model allows simultaneous listening and speaking, including immediate interruption. Qwen says it can respond more slowly and empathetically when it detects a low mood. Alibaba said prices would fall by about 70 percent for TTS, roughly 85 percent for Realtime and up to 95 percent for ASR.
Written by Sakhanda Wire AI from reporting by The Decoder. Facts, quotes and full context are in the original article below.