阿里 Qwen 发布 Qwen-Audio-3.1 五款语音模型，语音价格最高下调 95%

Alibaba launches Qwen Audio 3.1 with new models and slashes AI audio prices by up to 95 percent

AI 导读

阿里 Qwen 团队发布 Qwen-Audio-3.1，包含五款覆盖语音识别（ASR）、语音合成（TTS）和实时交互的模型。ASR 改进多语言和方言识别并自动清理填充词，ASR-Next 支持多说话人识别、时间戳及情绪和环境声检测；TTS-Next 将语言模型与扩散方法结合，可一次性生成语音、音效和背景音频。同步降价：TTS 约 70%，Realtime 约 85%，ASR 最高 95%。

正文 · 原文

Alibaba's AI team Qwen has released Qwen-Audio-3.1, a lineup of five models for speech recognition (ASR), text-to-speech (TTS), and real-time interaction. The ASR model improves multilingual and dialect recognition and automatically cleans up filler words and repetitions. ASR-Next adds multi-speaker identification with timestamps and detects emotions, ambient sounds, and machine noise. TTS handles multilingual synthesis with natural cross-language voice transfer. Users control emotion, speed, and style through simple text prompts like "Read this with a sharp, commanding tone, demanding respect."

TTS-Next pairs a language model with a diffusion approach to generate voice, sound effects, and background audio in a single pass. The real-time model supports simultaneous speaking and listening with instant interruption. When it detects a low mood, it responds more slowly and with more empathy, according to Qwen. Alibaba is also slashing prices. TTS drops about 70 percent, Realtime roughly 85 percent, and ASR up to 95 percent. More details on the blog and on Qwen Cloud.