Gpt Home alternatives for AI agents.

turnkey self-hosted offline transcription and diarization service with llm summary

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！

基于PaddlePaddle实现的语音识别，中文语音识别。项目完善，识别效果好。支持Windows，Linux下训练和预测，支持Nvidia Jetson开发板预测。

Mac compatible Ollama Voice

AI-powered multi-voice audiobook generator — LLM script annotation, voice cloning, voice design, LoRA training, per-line style control, and export to MP3, chaptered M4B, or Audacity multi-track. Built on Qwen3-TTS.

Optimized Whisper models for streaming and on-device use

Local voice chatbot for engaging conversations, powered by Ollama, Hugging Face Transformers, and Coqui TTS Toolkit

On-device Speech-to-Intent engine powered by deep learning

On-device streaming speech-to-text engine powered by deep learning

A SOTA Industrial-Grade All-in-One ASR system with ASR, VAD, LID, and Punc modules. FireRedASR2 supports Chinese (Mandarin, 20+ dialects/accents), English, code-switching, and both speech and singing ASR. FireRedVAD supports speech/singing/music in 100+ langs. FireRedLID supports 100+ langs and 20+ zh dialects. FireRedPunc supports zh and en.

The hub for audio AI research: papers, open models, benchmarks & datasets across audio LLMs, speech recognition, TTS, music & audio generation.

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

Local, OpenAI-compatible text-to-speech (TTS) API using Chatterbox, enabling users to generate voice cloned speech anywhere the OpenAI API is used (e.g. Open WebUI, AnythingLLM, etc.)

📦 快速转化「中文数字」和「阿拉伯数字」～ (最新特性：分数，日期、温度等转化）

speech to text benchmark framework

Foundational Model for Speech Recognition Tasks