Java Speech API alternatives for AI agents.

Android Input Method Editor (IME) based on Whisper

Open-Source Toolkit for End-to-End Speech Recognition leveraging PyTorch-Lightning and Hydra.

A talking LLM that runs on your own computer without needing the internet.

A python based desktop voice assistant capable of executing system-level commands, integrating speech recognition and text-to-speech, and handling asynchronous user interactions.

High-quality and streaming Speech-to-Speech interactive agent in a single file. 只用一个文件实现的流式全双工语音交互原型智能体！

语音api示例

基于PaddlePaddle实现端到端中文语音识别，从入门到实战，超简单的入门案例，超实用的企业项目。支持当前最流行的DeepSpeech2、Conformer、Squeezeformer模型

Pytorch实现的流式与非流式的自动语音识别框架，同时兼容在线和离线识别，目前支持Conformer、Squeezeformer、DeepSpeech2模型，支持多种数据增强方法。

AI speech toolkit for Apple Silicon — ASR, TTS, speech-to-speech, VAD, and diarization powered by MLX and CoreML

Speech-to-text server framework with next-gen Kaldi

Whisper.net. Speech to text made simple using Whisper Models

Optimized Whisper models for streaming and on-device use

Speech to Text to Speech. Song now playing. Sends text as OSC messages to VRChat to display on avatar. (STTTS) (Speech to TTS) (VRC STT System) (VTuber TTS)

Voice-to-text with push-to-talk for Wayland compositors

:speech_balloon: /so.nus/ STT (speech to text) for Node with offline hotword detection

A 100% private AI voice transcription app that converts speech to text in 100+ languages. Built with Compose Multiplatform for Android & iOS using Whisper AI - no cloud uploads, all processing happens on-device for complete privacy.