R_REDDYX.XYZ

ASR: open-source projects on GitHub

29 repositories on ASR, picked by the REDDYX AI agent. Each has a summary, key features and a breakdown. Sorted by stars.

// RELATED TOPICS

Speech To Text 66LLM 2094TTS 55Speech Recognition 36Transcription 28Whisper 49Text To Speech 72Ollama 249Speech Synthesis 14Audio 15Video 41Chinese 33Pytorch 98Tauri 105
NVIDIA-NeMo/Speech

NVIDIA NEMO SPEECH — FRAMEWORK FOR SPEECH AI AND MULTIMODAL LLMS

Scalable framework for ASR, TTS, and speech LLMs. Enables creating, customizing, and deploying speech models with ready checkpoints.

★ 18,764 · Python
modelscope/FunASR

FunASR — Speech Recognition

Industrial speech recognition tool: 170× realtime, 50+ languages, diarization, emotion detection, streaming, and OpenAI‑compatible API.

★ 16,235 · Python
k2-fsa/sherpa-onnx

OFFLINE SPEECH PROCESSING ON ONNXRUNTIME

Library for speech recognition and synthesis, diarization and audio enhancement. Runs locally on 12 programming languages and embedded systems without internet.

★ 16,007 · C++
FunAudioLLM/SenseVoice

SenseVoice: Voice Understanding Model

Multilingual model for analyzing and understanding speech in different languages with high accuracy.

★ 8,171 · Python
modelscope/FunClip

FUNCLIP: VIDEO EDITOR WITH AI

FunClip is an open-source tool for accurate speech recognition in video and quick clip creation using LLM. Easy to use, supports Python.

★ 6,562 · Python
umlx5h/LLPlayer

LLPlayer - LANGUAGE LEARNING

Media player for language learning with dual subtitles, AI subtitles, and real‑time translation.

★ 4,725 · C#
0xShug0/audio.cpp

Pure C++ Audio Inference Engine

All-in-one C++ inference engine for audio models (TTS, STT, VAD, voice conversion, music generation) powered by ggml, with zero Python dependencies and highly optimized p

★ 4,234 · C++
sgl-project/sglang-omni

SGLANG-OMNI: OMNI-SERVICE FOR AI

SGLang-Omni provides high-performance execution of TTS, ASR, and speech omni-models on Python.

★ 1,791 · Python
yuezhiai/jonex

JONEX UNIVERSAL MULTIMODAL PARSER

Jonex — universal parsing engine for multimedia, text and code, extended with ontology and LLM‑wiki. It indexes data, builds a knowledge graph and provides ready‑to‑use p

★ 1,675 · Python
tuya/TuyaOpen

TUYAOPEN – AI+IoT FRAMEWORK IN C

TuyaOpen is a framework for rapid integration of AI agents with IoT devices on T2/T3/T5AI and ESP32 platforms, written in C.

★ 1,579 · C
Open-Less/openless

Voice input with AI processing

Hold the key, speak, release — AI-enhanced text will appear next to the cursor in any application.

★ 1,356 · HTML
amicalhq/amical

AI Dictation Without Keyboard

Open AI assistant for dictation, working locally and offline. Type three times faster without a keyboard.

★ 1,307 · TypeScript
mbailey/voicemode

VOICEMODE - NATURAL VOICE CLOUD

Natural voice dialogues with Claude Code right in the terminal. voicemode turns text into lively speech of the AI assistant.

★ 1,214 · Python
Nomily-Ai/nomily-app

BYOK Voice Recording Companion

A voice recording app that transcribes audio, identifies speakers, and generates AI summaries using your own API keys.

★ 1,011
huggingface/optimum-intel

OPTIMUM-INTEL - ACCELERATE INFERENCE WITH INTEL

Optimum Intel provides Intel tools to accelerate AI model inference, simplifying deployment and boosting performance.

★ 630 · Jupyter Notebook
zenstory-ai/video-recap-skills

VIDEO RECAP WITH CLAUDE CODE

The project provides Claude Code skills for creating Chinese narration recaps from video files. It exports the result as an editable JianYing/CapCut draft. It runs locall

★ 626 · Python
SAOS-3624/dsh-video-storyboard

VIDEO STORYBOARD IN ONE IMAGE

dsh-video-storyboard creates a scene-aware storyboard for DeepSeek Harness: 9-16 cells with timestamps, transcript, and audio envelope in one image (384 tokens). Two tool

★ 542 · JavaScript
PiSugar/whisplay-ai-chatbot

WHISPLA AI CHATBOT ON RPI

A compact AI chatbot on Raspberry Pi Zero 2W, written in TypeScript. Easy to deploy and chat with LLM.

★ 536 · TypeScript
FireRedTeam/FireRedASR2S

FIRE RED ASR2S SOTA RECOGNITION

Full-featured industrial ASR system with speech recognition, VAD, LID, and punctuation, supporting Chinese, English, code-switching, and singing.

★ 528 · Python
AudarAI/Audar-ASR-V1

Audar-ASR-V1: Generative ASR

The project presents an Arabic-first generative speech recognition system with Flash and Turbo models, ranking first on the Open Universal Arabic ASR leaderboard. Include

★ 503 · Python
kigner/audio.cpp-webui

audio.cpp WebUI C++

Full‑featured web UI for audio model inference in pure C++ using ggml. Supports TTS, ASR/STT, VAD, speaker diarization, voice conversion, and music generation without Pyt

★ 431 · C++
mahimairaja/voiceai

VOYSAI: AGENT TEMPLATES

A collection of useful articles and links for creating voice AI agents. Quickly start with ready-made templates and resources.

★ 341
timoncool/speech-studio

OFFLINE AI VOICE STUDIO IN RUST

Local app for speech synthesis and recognition with voice cloning and speaker diarization. Works offline, downloads models automatically, supports MCP for AI agents.

★ 312 · Rust
XimilalaXiang/DeLive

DELIVE - AUDIO CAPTURE + AI SUBTITLES

Captures system audio, transcribes with 12 ASR engines across 60+ languages, and provides an AI workspace for summaries, chat, and mind maps.

★ 261 · TypeScript
roryeckel/wyoming_openai

Wyoming OpenAI Proxy

OpenAI API-compatible middleware that proxies requests via the Wyoming protocol for voice assistants.

★ 228 · Python
mallahyari/nemotron-asr-streaming-farsi

Streaming Farsi ASR Fine-Tuning

Fine-tunes NVIDIA Nemotron 3.5 ASR for streaming Persian speech with data prep, training, evaluation, and inference scripts.

★ 72 · Python
tancheng33/tingo

Local AI Meeting Assistant

Local-first AI meeting notes for Mac with on-device transcription, speaker diarization, and auto-generated minutes linked to audio quotes. Supports Tencent Meeting, Feish

★ 45 · Rust
Soul-AILab/SoulX-Transcriber

SoulX-Transcriber Speech Transcriber

End-to-end framework for multi-speaker transcription that simultaneously determines who speaks, when, and what is said. Implemented in Python.

★ 33 · Python
BillLucky/echocut

EchoCut: AI Video Converter

The project allows you to turn raw video recordings into finished branded content, optimized for any platforms, using local FFmpeg, WhisperX/MLX, and Ollama models in one

★ 31 · JavaScript

New projects on this topic in Telegram

Telegram →
ASR — 29 open-source GitHub projects | REDDYX AI