Alternatives and similar repositories for voice-to-voice-llm-structure

Users that are interested in voice-to-voice-llm-structure are comparing it to the libraries listed below

• xinhecuican / QSmartAssistant
  一个模块化，全过程可离线，低占用率的对话机器人/智能音箱
  ☆113Updated 7 months ago
• RemSynch / SenseVoice-Real-Time
  简单实现VAD+声纹锁+SenseVoice完成类语音实时转录的小项目
  ☆38Updated last year
• RapidAI / RapidTTS
  A cross platform implementation of Text-to-Speech based on ONNXRuntime.
  ☆32Updated 2 years ago
• huakunyang / SummerAsr
  SummerAsr 是一个基于C++的可独立编译且几乎没有额外依赖库的本地中文语音识别器。 Summer Asr is a Chinese automatic speech recognize project written with C++ that can be eas…
  ☆99Updated 10 months ago
• peilongchencc / My-FunASR
  基于FunASR实现语音识别，包含常规版和ONNX版(推荐)。
  ☆45Updated last year
• heyudage / VoiceTyping
  通过语音（说话）即可完成实时文本输入。通过PaddleSpeech项目二次开发 完成，支持离线脱网环境部署，支持GPU推理，目前客户端仅支持Windows。
  ☆25Updated 2 years ago
• DakeQQ / Voice-Activity-Detection-VAD-ONNX
  Utilizes ONNX Runtime for speech activity detection.
  ☆34Updated last month
• duj12 / ASR-2Pass
  ASR 2Pass onnxruntime and websocket server, based on FunASR(https://github.com/alibaba-damo-academy/FunASR).
  ☆81Updated this week
• chenyangMl / keyword-spot
  端到端语音唤醒工具箱，从模型训练到模型推理。
  ☆138Updated 2 months ago
• swordswind / cosyvoice_simple_api
  CosyVoice语音合成简易API
  ☆13Updated last year
• lovemefan / SenseVoice-python
  SenseVoice-python: A enterprise-grade open source multi-language asr system from funasr opensource with onnxruntime
  ☆106Updated 3 weeks ago
• lovemefan / fsmn-vad
  A enterprise-grade Voice Activity Detector from modelscope and funasr.
  ☆114Updated 2 years ago
• FeiGeChuanShu / FunASR-demo-ncnn
  some ncnn demos of FunASR
  ☆27Updated last year
• xingxing2233 / DH-Live-Web-UI
  DH-Live-Web-UI
  ☆18Updated last year
• jundaychan / funasr-fastapi
  funasr语音转文字的简单api版本，funasr+fastapi，方便部署在服务器上
  ☆13Updated last year
• Tzenthin / wenet_mnn
  语音识别模型pytorch转ONNX转MNN，C++实现部署
  ☆78Updated 3 years ago
• sepnic / litevad
  Speech-end detection library, based on WebRTC's VAD engine
  ☆26Updated 5 months ago
• LuckLittleBoy / SenseVoice-OneApi
  基于SenseVoice的funasr版本进行的api发布，可以无缝对接oneapi
  ☆83Updated last year
• HG-ha / SenseVoice-Api
  阿里SenseVoice的fastpi封装，采用onnx发布，体积更小，附带量化模型，支持GPU。支持从URL文件进行语音识别。
  ☆103Updated last year
• lovemefan / paraformer.cpp
  Port of Funasr's Paraformer model in C/C++
  ☆35Updated last year
• Ninot1Quyi / Qwen2.5-Omni-multimodal-chat
  基于通义千问 Qwen2.5-Omni 的实时语音对话系统，使用在线API服务，支持实时语音交互、动态语音活动检测和流式音频处理。A real-time voice conversation system based on Qwen2.5-Omni Online-API, …
  ☆78Updated 5 months ago
• hpc203 / Real-Time-Frame-Interpolation-onnxrun
  使用onnxruntime部署实时视频帧插值，包含C++和Python两个版本的程序
  ☆27Updated last year
• Ikaros-521 / voice_talk_chatgpt
  基于Gradio开发的ChatGPT聊天应用，可以文字 或 语音对话，发送的音频通过OpenAI的STT转文本后，再通过ChatGPT生成回复，回复的内容通过OpenAI TTS合成后返回并自动播放，实现语音聊天功能。
  ☆35Updated last year
• apinge / MeloTTS.cpp
  A lightweight pure C++ Text-to-Speech (TTS) pipeline with OpenVINO, supporting multiple languages.
  ☆84Updated last month
• shenduldh / CosyVoice2-Lightning
  Lightning-responsive CosyVoice2 streaming API based on FastAPI.
  ☆19Updated 3 weeks ago
• DakeQQ / Automatic-Speech-Recognition-ASR-ONNX
  Utilizes ONNX Runtime to transcribe audio into text.
  ☆57Updated last month
• DataXujing / DeepSeek-R1-Android
  安卓手机部署DeepSeek-R1 蒸馏的1.5B模型
  ☆22Updated 8 months ago
• CyberWon / ChatTTS-API
  ChatTTS HTTP API
  ☆54Updated last year
• pengzhendong / streaming-sensevoice
  Pseudo Streaming SenseVoice with Hotwords
  ☆369Updated 7 months ago
• muggle-stack / e2e_voice
  End to End Voice
  ☆28Updated last week