kadirnar/VoiceHub

VoiceHub: A Unified Inference Interface for TTS Models

56
/ 100
Established

Abstracts multiple TTS architectures (Orpheus, Dia, Vui, Kokoro, Chatterbox, EchoTTS) behind a single `AutoInferenceModel` API, supporting features like voice selection, speaker audio cloning, and language codes. Built on a factory-pattern loader that handles model-specific parameter mappings while maintaining consistent inference signatures across heterogeneous backends. Enables GPU acceleration via CUDA and outputs directly to WAV files or audio objects.

Available on PyPI.

Maintenance 10 / 25
Adoption 13 / 25
Maturity 24 / 25
Community 9 / 25

How are scores calculated?

Stars

69

Forks

5

Language

Python

License

Apache-2.0

Last pushed

Mar 02, 2026

Monthly downloads

112

Commits (30d)

0

Dependencies

10

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/kadirnar/VoiceHub"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.