# Fish Speech

> Fish Audio's multilingual TTS and voice cloning model

- Category: [Foundation Models](https://ailandscape.org/category/foundation-models) › Speech & Audio Models
- Homepage: https://fish.audio
- Repository: https://github.com/fishaudio/fish-speech
- Tags: tts, voice-cloning, multilingual, open-weights
- Also known as: Fish Audio S2, OpenAudio
- Added to the landscape: 2026-10-09

## Similar tools in Speech & Audio Models

- [Bark](https://ailandscape.org/tool/bark): Suno's early open text-to-audio model, no longer actively updated
- [Chatterbox](https://ailandscape.org/tool/chatterbox): Resemble AI's MIT-licensed TTS with emotion control and cloning
- [CosyVoice](https://ailandscape.org/tool/cosyvoice): Alibaba's multilingual streaming TTS with zero-shot voice cloning
- [Dia](https://ailandscape.org/tool/dia): Nari Labs' open dialogue TTS with nonverbal cues like laughter
- [IndexTTS](https://ailandscape.org/tool/indextts): Bilibili's zero-shot TTS with emotion and duration control
- [Kokoro](https://ailandscape.org/tool/kokoro): Lightweight 82M Apache 2.0 TTS model with high quality output
- [MusicGen](https://ailandscape.org/tool/musicgen): Meta's controllable text-to-music generation model
- [Sesame CSM](https://ailandscape.org/tool/sesame-csm): Sesame's conversational speech model for natural voice dialogue

---

Part of [AI Landscape](https://ailandscape.org), an open map of the AI ecosystem. Web page: https://ailandscape.org/tool/fish-speech · Index for AI assistants: https://ailandscape.org/llms.txt