Skip to content

Add Qwen3-TTS and Qwen3-ASR #369

@JamesClarke7283

Description

@JamesClarke7283

A really good TTS model has been released by Qwen, it supports voice cloning and is really good for this task, to the point where you can't tell the difference with a quality reference audio and the transcribed text input.

Qwen3-TTS:
https://qwen.ai/blog?id=qwen3tts-0115

Demo here:
https://huggingface.co/spaces/Qwen/Qwen3-TTS

Also a really good ASR model has been released by Qwen.

https://qwen.ai/blog?id=qwen3asr

Demo here:
https://huggingface.co/spaces/Qwen/Qwen3-ASR

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions