Kotlin Multiplatform Mobile Text-to-speak SDK for using either native TTS or Supertonic

100% in-browser, hands-free AI voice chat using Whisper, WebLLM, and Supertonic TTS

Lightning-Fast, On-Device TTS — running natively via ONNX.

A Toolkit to Help Optimize Onnx Model

Python library for audio and music analysis

Omnilingual ASR Open-Source Multilingual SpeechRecognition for 1600+ Languages

Lightning-Fast, On-Device, Multilingual TTS — running natively via ONNX.

MFCC-based LipSync plug-in for Unity using Job System and Burst Compiler

TTS model capable of streaming conversational audio in realtime.

Plug-and-play TTS integration toolkit powered by Kokoro-82M. Python + CLI interface. Lightweight, open-source, and ready for real-world use.

Towards Human-Sounding Speech

The best ChatGPT that $100 can buy.

Generate audiobooks from EPUBs, PDFs and text with synchronized captions.

Text-audio foundation model from Boson AI

[NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL

💬 Chat with anyone on any website.

A Japanese Tokenizer for Business

SoTA open-source TTS

(NeurIPS 2024 Oral 🔥) Improved Distribution Matching Distillation for Fast Image Synthesis

🎛 🔊 A Python library for audio.

Viterbi decoding in PyTorch

[ICLR 2024] Continual Momentum Filtering on Parameter Space for Online Test-time Adaptation.

Code and materials for ICML2024 submission

An unofficial PyTorch implementation of the StreamVC(Real-Time Low-Latency Voice Conversion)

Generative models for conditional audio generation

Kolmogorov Arnold Networks