cinemasetfree.com
← Back to all generators
camenduru/metavoice
Official
View on Replicate →
MetaVoice-1B: 1.2B parameter base model trained on 100K hours of speech
Capabilities
No capability data available
Cost
Community model (estimated from hardware time)
Input Parameters
| Name | Type | Description | Default | Constraints |
|---|---|---|---|---|
input_audio * | string (uri) | Input Image | — | — |
text | string | — | "This is a demo of text to speech by MetaVoice-1B, an open-source foundational audio model by MetaVoice." | — |
input_audio required string Input Image
text string Default:
"This is a demo of text to speech by MetaVoice-1B, an open-source foundational audio model by MetaVoice." Version:
713109ece68b Updated: 2/26/2026 13.5K runs