"speech-processing"

espnet/espnet

espnet — End-to-End Speech Processing Toolkit

Python★ 9.9k⑂ 2.4kai-ml

☆

coqui-ai/TTS

TTS — 🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

Python★ 45.8k⑂ 6.2kai-ml

☆

handy-computer/transcribe.cpp

transcribe.cpp — ggml speech-to-text inference for 16+ model families

C++★ 1.4k⑂ 35other

+395 ★☆

mozilla/DeepSpeech

DeepSpeech — DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.

C++★ 26.8k⑂ 4.1kai-ml

☆

babysor/MockingBird

MockingBird — 🚀Clone a voice in 5 seconds to generate arbitrary speech in real-time

Python★ 36.9k⑂ 5.2kai-ml

☆

CorentinJ/Real-Time-Voice-Cloning

Real-Time-Voice-Cloning — Clone a voice in 5 seconds to generate arbitrary speech in real-time

Python★ 60k⑂ 9.4kai-ml

☆

moonshine-ai/moonshine

moonshine — Very low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces

C++★ 10.1k⑂ 526ai-ml

+282 ★☆

langchain-ai/open_deep_research

open_deep_research —

Python★ 12.2k⑂ 1.7kother

+14 ★☆

andrewyng/context-hub

context-hub —

JavaScript★ 13.8k⑂ 1.2kweb

☆

MiniMax-AI/skills

skills —

C#★ 13.1k⑂ 1.1kother

☆

RVC-Project/Retrieval-based-Voice-Conversion-WebUI

Retrieval-based-Voice-Conversion-WebUI — Easily train a good VC model with voice data <= 10 mins!

Python★ 36.5k⑂ 5.1kdata

☆

hankcs/HanLP

HanLP — Natural Language Processing for the next decade. Tokenization, Part-of-Speech Tagging, Named Entity Recognition, Syntactic & Semantic Dependency Parsing, Document Classification

Python★ 36.5k⑂ 10.9kai-ml

☆

myshell-ai/OpenVoice

OpenVoice — Instant voice cloning by MIT and MyShell. Audio foundation model.

Python★ 37k⑂ 4.1kother

☆

explosion/spaCy

spaCy — 💫 Industrial-strength Natural Language Processing (NLP) in Python

Python★ 33.8k⑂ 4.7kai-ml

☆

FunAudioLLM/CosyVoice

CosyVoice — Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

Python★ 22.1k⑂ 2.6kai-ml

☆

snakers4/silero-vad

silero-vad — Silero VAD: pre-trained enterprise-grade Voice Activity Detector

Python★ 9.6k⑂ 804ai-ml

☆

KoljaB/RealtimeSTT

RealtimeSTT — A robust, efficient, low-latency speech-to-text library with advanced voice activity detection, wake word activation and instant transcription.

Python★ 10k⑂ 850other

☆

huggingface/transformers

transformers — 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Python★ 162.7k⑂ 33.9kai-ml

☆

supertone-inc/supertonic

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

Swift★ 13.4k⑂ 1.4kmobile

☆

sinaptik-ai/pandas-ai

pandas-ai — Chat with your database or your datalake (SQL, CSV, parquet). PandasAI makes data analysis conversational using LLMs and RAG.

Python★ 23.7k⑂ 2.3kdata

☆

keras-team/keras

keras — Deep Learning for humans

Python★ 64.2k⑂ 19.7kai-ml

☆

interviewstreet/hiring-agent

hiring-agent — AI agent to evaluate and score resumes.

Python★ 2.5k⑂ 623ai-ml

+203 ★☆

open-mmlab/Amphion

Amphion — Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audio, music, and speech generation research and development.

Python★ 10k⑂ 829other

☆

AudioKit/AudioKit

AudioKit — Audio synthesis, processing, & analysis platform for iOS, macOS and tvOS

Swift★ 11.4k⑂ 1.6kmobile

☆

2noise/ChatTTS

ChatTTS — A generative speech model for daily dialogue.

Python★ 39.7k⑂ 4.2kai-ml

☆

jamiepine/voicebox

voicebox — The open-source AI voice studio. Clone, dictate, create.

TypeScript★ 44.6k⑂ 5.4kai-ml

+821 ★☆

deepset-ai/haystack

haystack — Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.

MDX★ 25.9k⑂ 2.9kai-ml

☆

BVLC/caffe

caffe — Caffe: a fast open framework for deep learning.

C++★ 34.6k⑂ 18.5kai-ml

☆

zesterer/chumsky

chumsky — [Chumsky has moved to Codeberg!] Write expressive, high-performance parsers with ease.

Rust★ 4.5k⑂ 210other

☆

karpathy/autoresearch

autoresearch — AI agents running research on single-GPU nanochat training automatically

Python★ 91.6k⑂ 13.1kai-ml

☆

pjreddie/darknet

darknet — Convolutional Neural Networks

C★ 26.5k⑂ 21kai-ml

☆

stanfordnlp/dspy

dspy — DSPy: The framework for programming—not prompting—language models

Python★ 36.2k⑂ 3.1kbackend

☆

harvard-edge/cs249r_book

cs249r_book — Machine Learning Systems

Python★ 27k⑂ 3.2kother

+329 ★☆

google-ai-edge/mediapipe

mediapipe — Cross-platform, customizable ML solutions for live and streaming media.

C++★ 36.2k⑂ 6.1kai-ml

☆