Samuel Vitorino

samuel-vitorino

1 1 4

AI & ML interests

None yet

Recent Activity

updated a model 4 days ago

samuel-vitorino/sopro-v2-turbo

liked a Space 6 days ago

Nymbo/Sopro-Voice-Clone

updated a model 7 days ago

samuel-vitorino/sopro-v2-turbo-onnx

View all activity

Organizations

updated a model 4 days ago

samuel-vitorino/sopro-v2-turbo

Text-to-Speech • 0.1B • Updated 4 days ago • 35.6k • 51

liked a Space 6 days ago

Sopro-Voice-Clone

🌬

Streaming zero-shot voice cloning with a 120M Sopro model.

updated a model 7 days ago

samuel-vitorino/sopro-v2-turbo-onnx

Text-to-Speech • Updated 7 days ago • 62 • 2

updated a Space about 1 month ago

Sopro v2 Turbo TTS

🗣

Zero-shot voice cloning TTS with 120M params

New activity in samuel-vitorino/sopro-v2-turbo about 1 month ago

Demo for this model on Spaces

❤️ 1

#1 opened about 1 month ago by

multimodalart

liked a Space about 1 month ago

Sopro v2 Turbo TTS

🗣

Zero-shot voice cloning TTS with 120M params

liked a model about 1 month ago

samuel-vitorino/sopro-v2-turbo

Text-to-Speech • 0.1B • Updated 4 days ago • 35.6k • 51

posted an update about 1 month ago

Post

309

Sopro V2 is out: open-source voice-cloning TTS at 120M params, Apache-2.0.

- Streams with ~300 ms time-to-first-audio on a laptop CPU (0.21 RTF, and 0.07 RTF on an H100)
- English, French, German, and native European Portuguese, to my knowledge a first for open TTS
- 1.51-1.65 WER on Seed-TTS-eval test-en, competitive with models 3-14x larger (F5-TTS 1.83, CosyVoice 3 2.02, Spark-TTS 1.98)
- Zero-shot cloning from 5-20 s of reference audio
- Also runs fully in the browser (WebGPU on desktop, quantized WASM on mobile)

Try it with one command:

uvx --from sopro soprotts serve

Weights: samuel-vitorino/sopro-v2-turbo
Evals, audio samples, and how it was built: https://research.haloneuro.ai/posts/sopro-v2
Code: https://github.com/samuel-vitorino/sopro