Alibaba drops five Qwen-Audio-3.1 voice models, cuts ASR pricing by 95%
aigclink · x · 2026-09-23
Alibaba released five Qwen-Audio-3.1 voice models with steep price cuts: ASR down 95%, Realtime down 85%, TTS down 70%, spanning understanding, generation, and real-time interaction.
- ASR: 30 languages + 16 Chinese dialects, native transcript cleanup, speaker-diarized output with timestamps, 160ms first-token streaming latency
- ASR-Next: goes beyond transcription to interpret emotion, ambient sounds, and answer audio questions
- TTS: cross-lingual voice consistency with emotion and speed control
- TTS-Next: generates complete audio works (voice + sound effects + ambience) at 48kHz, targeting podcasts, audiobooks, film, and games
- Realtime: full-duplex, interruptible, emotion-aware, seamless language switching, and can invoke agent tools mid-conversation
The author argues real-time voice is shifting from a "feature" to an "interaction entry point", with implications for customer service, assistants, and screenless hardware like AI glasses.
Related event: Alibaba Qwen Releases Five Qwen-Audio-3.1 Models with Massive Price Cuts(6 posts)→
More from Models
- Opus 5.5 feels nerfed — user blames system prompt restrictions, not the model — oyacaro · 2026-11-12
- ChatGPT now links to brand homepages far more, reshaping brand-mention tracking — lilyraynyc · 2026-11-12
- YC-backed Monte launches post-training platform to build proprietary models from your agents' real work — ycombinator · 2026-11-12
- Leak Claims OpenAI Will Launch Entire GPT-6.2 Family Tomorrow to Counter Opus 5.5 and Fable 5.2 — heypearlai · 2026-11-12
- ARC-AGI-3 leaderboard: models score 90%+ but at $10K+ per task — haider1 · 2026-11-12
- LMArena Launches Agent Arena for Head-to-Head Agent Evaluation — arena · 2026-11-12