Qwen-Audio-3.1: Alibaba's Five-Model Audio Stack

Melvin Vivas · X post · 2026-09-23 · Open on X

Topics: Industry Trends & Job Market, LLM Fundamentals · Level: beginner

Summary

Alibaba Qwen released Qwen-Audio-3.1, which upgrades its speech recognition (ASR), text-to-speech (TTS) and Realtime models. It also adds two new models: TTS-Next for audio creation and ASR-Next for audio understanding. Together the five models cover understanding, generation, interaction and creation, and Qwen announced big price cuts.

Key points

• Qwen-Audio-3.1 upgrades the ASR, TTS and Realtime models.
• New TTS-Next model: for audio creation.
• New ASR-Next model: for audio understanding.
• Five models make up one audio stack covering understanding, generation, interaction and creation.
• Qwen announced big price cuts across the line-up (the quoted post is cut off before the details).

Resources mentioned

• Qwen (@Alibaba_Qwen) on X · person · x.com · free
  Official X account of Alibaba's Qwen team, which posts model releases and demos.
  Also in: Demo: Qwen3.8-27B Running Locally with Pi and llama.cpp (Melvin Vivas on X · notes), Running AI Locally: Rebuilding AIBackends as a Python Library with Open Models (Melvin Vivas on X · notes), Audio-Visual Vibe Coding with Qwen 3.5 Omni: Spoken Specs to Web App (Melvin Vivas on X · notes)
• Qwen TTS-Next · tool · x.com · paid
  Alibaba's audio model family with upgraded ASR, TTS and Realtime models.

Try this

• Follow @Alibaba_Qwen for audio model releases and compare Qwen's ASR/TTS models for voice applications.