Fish Speech S2 Pro – Voice Cloning & TTS
Fish Speech S2 Pro can clone voices from short audio samples and generate extremely natural speech in more than 80 languages.
You can even control delivery and emotion directly inside your script using tags like [excited], [whisper], or [angry]. With the ability to parse entire pages of text in a calm and paced manner, Fish Speech S2 is one of the most powerful open-source text-to-speech systems available right now.
Interfaces Included
- Simple Gradio WebUI for quick voice cloning and testing
- Advanced Awesome WebUI with additional workflow controls
- NodeJS required for Awesome WebUI (set up automatically by the Get Going Fast setup)
Key Capabilities
- Voice cloning from short reference audio
- Natural speech generation in 80+ languages
- Emotion and delivery control with inline script tags
- Long-form narration support for pages of text
Advanced Features
- Voice fine-tuning capability included in the repository
- Flexible inference workflows
- Designed for experimentation and voice creation projects
The repository also includes the ability to fine-tune voices, though that capability is not part of the basic demo workflow shown here.
Get Going Fast provides community setup guidance, documentation, tutorials, troubleshooting support, and member services. Get Going Fast does not sell, host, store, mirror, or redistribute AI model files, model weights, training datasets, or third-party project files.
When a setup guide references third-party dependencies, repositories, or model files, it points users to official upstream public sources such as GitHub, Hugging Face, package managers, or original project repositories, subject to those sources' own licenses, terms, and availability.
Get Going Fast is a general-audience AI education and workflow site, not an adult-content site or hosted AI generation service. Do not use Get Going Fast materials, support, guidance, or referenced third-party tools for unlawful, abusive, non-consensual, sexually explicit, exploitative, harassing, deceptive, or privacy-violating content, including misuse of another person's likeness, voice, identity, intellectual property, privacy, or publicity rights. See our Acceptable Use Policy.
If you are a rights holder, platform reviewer, payment processor, or hosting provider with a concern about a listed tool, guide reference, or upstream source, please contact us. We will review the concern promptly and remove or revise references when appropriate.
