Aevi's voice

AevumVoice.aar is the voice the Aevi iPhone app speaks with, packed as one Apple Archive. The app downloads it once, on Wi-Fi, and opens it only if its SHA-256 matches the one built into the app.

  • Size: 270,366,369 bytes
  • SHA-256: 70304f919ed0e59eb8edca751d3901e5b30f6b718f055cf28477ed4b6d5e6d67

Credits

What From Licence
The speech model, Pocket TTS Kyutai, https://github.com/kyutai-labs/pocket-tts CC BY 4.0
The voice "george" Kyutai, from speaker p315 of the VCTK corpus (University of Edinburgh, CSTR) CC BY 4.0
The Core ML conversion FluidInference, https://huggingface.co/FluidInference/pocket-tts-coreml (folder v2.1/english, revision 91748676fe3c8b2eb3007b3125253bcd898202c3) CC BY 4.0

Packed unchanged from the conversion above.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support