siva-sub/NekoSpeak
Private, offline AI Text-to-Speech for Android with Kokoro, KittenTTS, Pocket-tts and Piper models.
Implements ONNX Runtime inference with CPU optimization and multi-threading to run neural TTS models on-device, featuring an adaptive streaming architecture that auto-tunes buffer sizes based on device performance to balance latency and audio quality. Integrates with Android's TTS framework for system-wide compatibility across reading apps like MoonReader, while supporting voice cloning through custom audio enrollment and zero-shot synthesis capabilities.
Stars
43
Forks
6
Language
Kotlin
License
MIT
Category
Last pushed
Mar 07, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/siva-sub/NekoSpeak"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
thewh1teagle/kokoro-onnx
TTS with kokoro and onnx runtime
nazdridoy/kokoro-tts
A CLI text-to-speech tool using the Kokoro model, supporting multiple languages, voices (with...
met4citizen/HeadTTS
HeadTTS: Free neural text-to-speech (Kokoro) with timestamps and visemes for lip-sync. Runs...
Lyrcaxis/KokoroSharp
Fast local TTS inference engine in C# with ONNX runtime. Multi-speaker, multi-platform and...
remsky/Kokoro-FastAPI
Dockerized FastAPI wrapper for Kokoro-82M text-to-speech model w/CPU ONNX and NVIDIA GPU PyTorch...