Explore open-source TTS

Create a voice from a description, clone a reference speaker, or direct the delivery of Chinese and English speech.

• Voice design
• Voice cloning
• Voice direction

Embedded demo: 2

Clone a speaker while controlling emotion and speaking speed, with multilingual synthesis from a reference recording.

• Voice cloning
• Emotion control
• Speed control

Embedded demo: 2.5

A voice-cloning and text-to-speech toolkit for zero-shot inference and few-shot speaker adaptation across languages.

• Voice cloning
• Few-shot adaptation
• Cross-language speech

Embedded demo: V2 Pro Plus

Multilingual voice generation with cross-language cloning and natural-language control over delivery, dialect and emotion.

• Cross-language cloning
• Instruction control
• Dialects

Embedded demo: Fun-CosyVoice3-0.5B-2512

A speech-generation family supporting custom voices, voice design and reference-based cloning with natural-language instructions.

• Voice design
• Voice cloning
• Instruction control

Embedded demo: Qwen3-TTS

Flow-matching speech synthesis that uses a reference recording and its transcript for zero-shot voice cloning.

• Zero-shot cloning
• Reference transcript
• Flow matching

Embedded demo: F5-TTS

Expressive multilingual text-to-speech and reference-based voice cloning from Resemble AI.

• Multilingual speech
• Voice cloning
• Expression control

Embedded demo: Multilingual V3

Generate expressive, multi-character speech with voice cloning, natural-language direction and support for longer scenes.

• Multi-character scenes
• Voice cloning
• Emotion direction

Embedded demo: Drama 3

Natural English speech synthesis using style diffusion and large speech language models, with reference-based speaker adaptation.

• Style diffusion
• Voice cloning
• English narration

Embedded demo: 2