---
id: "2026-01-22-qwen3-tts-asr-open-weights"
url: "https://postcutoff.com/e/2026-01-22-qwen3-tts-asr-open-weights/"
as_of: "2026-11-13T13:49:00+01:00"
date: "2026-01-22"
date_precision: day
category: open-source
importance: 3
confidence: high
status: [Confirmed]
sources: 5
editor: human editor
human_review: null
version: "2026-10-04"
---

As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/e/2026-01-22-qwen3-tts-asr-open-weights/

# Alibaba open-sources Qwen3-TTS and, a week later, Qwen3-ASR

Full title: Alibaba open-sources Qwen3-TTS (voice design, 3-second cloning, 97 ms streaming) and, a week later, Qwen3-ASR

On 2026-01-22 Alibaba's Qwen team released Qwen3-TTS under Apache-2.0 (0.6B and 1.7B checkpoints plus a 12 Hz tokenizer). It offers voice design from text descriptions, voice cloning from about 3 s of audio in 10 languages, and ~97 ms streaming latency. On 2026-01-29 Qwen3-ASR followed (0.6B/1.7B plus a forced aligner, 30 languages and 22 Chinese dialects). Both became among the most-downloaded open speech models of 2026.

## Key facts
- Qwen3-TTS repos: Qwen3-TTS-12Hz-{1.7B,0.6B}-{Base,CustomVoice}, 1.7B-VoiceDesign, Qwen3-TTS-Tokenizer-12Hz; tech report arXiv 2601.15621
- Languages (TTS): zh, en, ja, ko, de, fr, ru, pt, es, it; end-to-end latency as low as 97 ms; one model for streaming and non-streaming
- Qwen3-ASR (2026-01-29): 1.7B and 0.6B plus Qwen3-ForcedAligner-0.6B; 30 languages + 22 Chinese dialects, singing/music robust; self-reported AISHELL-2 WER 2.71 vs 5.06 for Whisper-large-v3
- Hugging Face downloads in the month to 2026-09-29: Qwen3-TTS-12Hz-1.7B-CustomVoice ~2.4M, Qwen3-ASR-1.7B ~1.76M
- Hosted equivalents: qwen3-tts-flash / qwen3-tts-instruct-flash on Model Studio; superseded in Alibaba's API lineup by Qwen-Audio-3.0 (Jul 2026) and 3.1 (Sep 2026)

## What happened

Qwen released a complete open TTS family with voice design, cloning and low-latency streaming, then an open ASR family
with a forced aligner for timestamps a week later, both under Apache-2.0.

## Why it matters

Voice cloning and voice design had mostly been proprietary (ElevenLabs and others). Qwen3-TTS made them freely
self-hostable, and it became one of the most-downloaded speech models of 2026.

## Your AI and this story

- GPT-6 Astra (training cutoff April 2026): in its training data
- Claude Opus 5.5 (training cutoff June 2026): in its training data
- Gemini 4 Hydrogen (training cutoff March 2026): in its training data
- Grok 4.7 (training cutoff May 2026): in its training data

## Sources

1. [GitHub - QwenLM/Qwen3-TTS](https://github.com/QwenLM/Qwen3-TTS) (github.com, code)
2. [arXiv 2601.15621 - Qwen3-TTS technical report](https://arxiv.org/abs/2601.15621) (arxiv.org, paper)
3. [Hugging Face - Qwen3-TTS-12Hz-1.7B-CustomVoice](https://huggingface.co/Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice) (huggingface.co, code)
4. [GitHub - QwenLM/Qwen3-ASR](https://github.com/QwenLM/Qwen3-ASR) (github.com, code)
5. [Hugging Face - Qwen3-ASR-1.7B](https://huggingface.co/Qwen/Qwen3-ASR-1.7B) (huggingface.co, code)

## Changes

- 2026-09-29 (filed): Created

## Related

- 2026-09-23: [Alibaba launches Qwen-Audio-3.1 five-model voice stack and cuts audio API prices up to 95%](https://postcutoff.com/e/2026-09-23-qwen-audio-3-1/index.md)
- 2026-07-20: [Alibaba's Qwen-Audio-3.0-TTS takes #1 on the Artificial Analysis text-to-speech leaderboard](https://postcutoff.com/e/2026-07-20-qwen-audio-3-0-tts/index.md)
- 2026-03-09: [Fish Audio open-sources S2](https://postcutoff.com/e/2026-03-09-fish-audio-s2-open-source/index.md)
- Models: [Qwen3-ASR (0.6B / 1.7B) + Qwen3-ForcedAligner](https://postcutoff.com/m/qwen3-asr/) (`qwen3-asr`), [Qwen3-TTS (open weights 0.6B / 1.7B; API qwen3-tts-flash)](https://postcutoff.com/m/qwen3-tts/) (`qwen3-tts`)