All the models in one place
Run Zonos Text to Speech and every other model on Glif from one chat. One account, one balance, no API keys to wire up.
Zonos Text to Speech
Test outputs
Compare all modelsZonos Text to Speech in practice
What it does and when to use it.
Model summary
Zyphra’s Zonos v0.1 turns text into speech using a voice sample. Provide up to 4,096 characters and a recording of the voice you want to use. Glif charges per generation, not per character. There are no separate controls for style, emotion, or speech rhythm.
Capabilities
Text to speech
Speech synthesis
Voice cloning via sample
Speaker conditioning
Transformer
Audio generation
Suggested use cases
- Text-to-speech for app and product UX
- Narration for articles, docs, and blog posts
- Voiceover generation for videos and demos using a speaker sample to clone the target voice
- Accessibility readouts for written content
- Automated voice responses for agents/IVR prototypes