Qwen3-TTS

Local text-to-speech models generate multilingual audio with voice cloning and description-based voice design under the Apache 2.0 license.

Qwen3-TTS is a family of local text-to-speech models for developers building speech applications or creating audio with custom voices.

Voice cloning: Base models can clone a voice from a reference recording as short as three seconds. Cloning normally uses the recording's transcript; an audio-only mode trades some quality for convenience.
Voice design: Describe a voice in natural language, then use the generated recording with a Base model to reuse that voice across multiple lines.
Delivery control: The larger CustomVoice model accepts instructions for tone, emotion, and speaking style. Preset speakers include Chinese dialect profiles.
Multilingual speech: Generate audio in Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, and Italian.
Streaming audio: Models support both streaming speech output for interactive applications and generation of complete audio clips. The Python package also supports batch generation.

The project is open source under Apache 2.0. You can run it through the qwen-tts Python package or a browser-based local demo. vLLM-Omni provides an offline inference route with downloaded weights. CUDA GPU execution is supported. DashScope provides a separate, optional cloud API.

Capabilities depend on the model: VoiceDesign handles description-based voices, CustomVoice supplies preset speakers, and Base handles cloning and fine-tuning. Natural-language delivery control requires the larger CustomVoice model.

Text-to-Speech Models Text-to-Speech and Audiobooks Voice Cloning and Voice Changers Web Batch processing Hugging Face integration Multilingual Streaming inference Voice cloning Works offline

Nobody has claimed Qwen3-TTS yet

Work on Qwen3-TTS? Claim this page and we'll verify you by hand. Qwen3-TTS gets the verified checkmark, and you can upgrade the listing.

Want more people to find it? Promote it

Something wrong or outdated on this page?

Logotyper

Got an idea for an AI tool? I'm Eugene, the designer and developer behind Localhosted. I'll help you build it, from the first sketch to launch.

Start your project

Similar to Qwen3-TTS

View all tools

CosyVoice

7 videos

A local text-to-speech system supports multilingual voice cloning and streaming audio, with open-source code under Apache 2.0.

24.4KUpdated 6 months agoApache-2.0

Linux · Docker · Web#Hugging Face integration#Multilingual#Streaming inference

CosyVoice is a text-to-speech system for developers building speech applications on their own hardware or self-hosted servers. It can generate speech in a reference speaker's voice, including in another language, without training a separate model for each speaker.

Text-to-Speech and AudiobooksText-to-Speech ModelsVoice Cloning and Voice Changers

IndexTTS

4 videos

Local text-to-speech software that clones a voice from one recording and supports multilingual speech with emotion and pronunciation controls.

25.1KUpdated 2 months ago

Windows · Linux · Web#Hugging Face integration#Multilingual#Multimodal input

IndexTTS is a local text-to-speech system for people creating spoken audio and developers adding speech generation to applications. It can reproduce a voice from a single reference recording.

Text-to-Speech and AudiobooksText-to-Speech ModelsVoice Cloning and Voice Changers

MOSS TTS

3 videos

An open-source text-to-speech model for multilingual narration and voice cloning, with pronunciation and timing controls, licensed under Apache 2.0.

4.3KUpdated 2 months agoApache-2.0

Web#Multilingual#Multimodal input#Streaming inference

MOSS TTS generates speech for developers and creators working on narration, dubbing and other long audio content. It supports consistent voices across long passages and can clone a speaker from reference audio without separate training for that voice.

Music and Sound ModelsOn-Device and In-Browser AIText-to-Speech and AudiobooksText-to-Speech ModelsVoice Cloning and Voice Changers

Spark-TTS

1 video

A local text-to-speech system built on Qwen2.5, with Chinese and English voice cloning, adjustable synthetic voices, and Apache 2.0 licensed code.

11KUpdated 2 years agoApache-2.0

macOS · Windows · Linux · Web#Hugging Face integration#Multilingual#Voice cloning

Spark-TTS is a local text-to-speech system for developers and researchers building speech applications. It can reproduce a voice from reference audio or create a synthetic speaker with chosen vocal traits.

Text-to-Speech and AudiobooksText-to-Speech ModelsVoice Cloning and Voice Changers

VoxCPM

2 videos

An open-source text-to-speech system generates multilingual audio locally, with voices designed from descriptions or cloned from recordings.

42.5KUpdated 6 days agoApache-2.0

macOS · Linux · Web#GGUF#Hugging Face integration#llama.cpp backend

VoxCPM is a local text-to-speech system for developers and audio creators who want to generate speech with voices they can design or clone. It supports multilingual narration and control over how a voice delivers the text.

Text-to-Speech and AudiobooksText-to-Speech ModelsVoice Cloning and Voice Changers

Dia

1 video

An open-source text-to-speech model that generates English dialogue locally, with voice cloning and NVIDIA GPU inference under Apache 2.0.

19.4KUpdated 12 months agoApache-2.0

Docker · Web#Hugging Face integration#Multimodal input#Voice cloning

Dia generates spoken English conversations from a written script. It's for developers and researchers who want to produce two-speaker dialogue on their own hardware, with audio references to guide the voices and delivery.

Text-to-Speech and AudiobooksText-to-Speech ModelsVoice Cloning and Voice Changers