Fish Speech

Health v2 · maintenance only

Flags: no_license

Adoption not part of the score

33062 stars · 2872 forks observed · 2026-10-14

What it is AI-extracted, prompt v1, taxonomy v1, 2026-10-05, confidence 0.97

Fish Speech is an open‑source, state‑of‑the‑art text‑to‑speech system built on transformer and VITS architectures. It provides a Python library, CLI, and Docker‑based inference server for high‑quality, expressive voice generation.

Use cases

• Convert plain text into natural, expressive speech for podcasts or audiobooks
• Clone a speaker’s voice and generate speech with fine‑grained emotional tags
• Integrate TTS into chatbots or virtual assistants via the provided API server
• Run batch TTS jobs on a GPU‑enabled Linux server or Docker container
• Create multi‑language voice outputs for international applications

When to choose

• You need high‑quality, open‑source TTS with support for many languages and emotions
• Your deployment environment is Linux or Docker and you have access to a GPU with ≥24 GB memory
• You want a flexible solution that offers both a Python library and a ready‑to‑run inference server

When to avoid

• You require native Windows or macOS support without Docker
• Your hardware cannot meet the GPU memory requirements for the full model
• You need a lightweight TTS model with minimal dependencies

Facets

application · maturity active

audio-processing nlp cli speech-processing python transformer vits vqgan vqvae llama reinforcement-learning-alignment multi-speaker prosody-control web-ui api-server natural-language-processing ai-agents linux docker gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="fishaudio/fish-speech")