Zyphra/Zonos

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

7244 stars · 815 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Zonos-v0.1 is an open-weight text-to-speech model trained on over 200k hours of multilingual speech, with a Python library for inference. It supports zero-shot voice cloning from short reference clips and fine-grained conditioning on speaking rate, pitch, quality, and emotions, outputting 44kHz audio.

Use cases

• generate natural speech from text
• clone a voice from a short audio sample
• create expressive TTS with emotion control
• build a multilingual voiceover generator
• run open-source TTS locally on GPU
• generate speech at 44kHz quality

When to choose

• you need high-quality open-weight TTS with voice cloning
• you want local inference without relying on hosted TTS APIs
• you need control over emotion, pitch, and speaking rate
• you need multilingual speech generation

When to avoid

• you need a lightweight CPU-only TTS solution
• you need a fully managed hosted service
• you need non-Python integration without GPU resources

Facets

library · maturity active

tts speech-recognition machine-learning deep-learning llm-inference speech-processing artificial-intelligence deep-learning python cross-platform text-to-speech voice-cloning open-weights multilingual gradio transformer audio-generation audio gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="Zyphra/Zonos")