#Speech

Showing 60 of 105 repositories tagged #speech, ranked by stars

coqui-ai
coqui-ai
TTS

๐Ÿธ๐Ÿ’ฌ - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

Score
73
โ˜… 45.7k โ‘‚ 6.1k +26/day
Python
babysor
babysor
MockingBird

๐Ÿš€Clone a voice in 5 seconds to generate arbitrary speech in real-time

Score
96
โ˜… 36.9k โ‘‚ 5.2k +7/day
Python
OpenBMB
OpenBMB
VoxCPM

VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning

Score
100
โ˜… 32.8k โ‘‚ 3.7k +878/day
Python
svc-develop-team
svc-develop-team
so-vits-svc

SoftVC VITS Singing Voice Conversion

Score
62
โ˜… 28.1k โ‘‚ 5.0k +8/day
Python
m-bain
m-bain
whisperX

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

Score
88
โ˜… 23.0k โ‘‚ 2.3k +224/day
Python
huggingface
huggingface
datasets

๐Ÿค— The largest hub of ready-to-use datasets for AI models with fast, easy-to-use and efficient data manipulation tools

Score
92
โ˜… 21.7k โ‘‚ 3.3k +7/day
Python
AIGC-Audio
AIGC-Audio
AudioGPT

AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head

Score
50
โ˜… 10.2k โ‘‚ 853 โ€”
Python
mozilla
mozilla
TTS

:robot: :speech_balloon: Deep learning for Text to Speech (Discussion forum: https://discourse.mozilla.org/c/tts)

Score
58
โ˜… 10.2k โ‘‚ 1.3k +3/day
Jupyter Notebook
snakers4
snakers4
silero-vad

Silero VAD: pre-trained enterprise-grade Voice Activity Detector

Score
85
โ˜… 9.5k โ‘‚ 799 +104/day
Python
modelscope
modelscope
modelscope

ModelScope: bring the notion of Model-as-a-Service to life.

Score
81
โ˜… 9.0k โ‘‚ 957 +2/day
Python
netease-youdao
netease-youdao
EmotiVoice

EmotiVoice ๐Ÿ˜Š: a Multi-Voice and Prompt-Controlled TTS Engine

Score
46
โ˜… 8.5k โ‘‚ 754 +1/day
Python
PaddlePaddle
PaddlePaddle
models

Officially maintained, supported by PaddlePaddle, including CV, NLP, Speech, Rec, TS, big models and so on.

Score
54
โ˜… 6.9k โ‘‚ 2.9k โ€”
Python
huggingface
huggingface
speech-to-speech

Build local voice agents with open-source models

Score
77
โ˜… 5.8k โ‘‚ 724 +275/day
Python
cactus-compute
cactus-compute
cactus

Low-latency AI engine for mobile devices & wearables

Score
100
โ˜… 5.4k โ‘‚ 435 +7/day
C++
fixie-ai
fixie-ai
ultravox

A fast multimodal LLM for real-time voice

Score
100
โ˜… 4.5k โ‘‚ 380 +2/day
Python
Rikorose
Rikorose
DeepFilterNet

Noise supression using deep filtering

Score
0
โ˜… 4.4k โ‘‚ 484 +20/day
Python
modelscope
modelscope
ClearerVoice-Studio

An AI-Powered Speech Processing Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Enhancement, Separation, and Target Speaker Extraction, etc.

Score
86
โ˜… 4.3k โ‘‚ 351 +8/day
Python
metavoiceio
metavoiceio
metavoice-src

Foundational model for human-like, expressive TTS

Score
89
โ˜… 4.2k โ‘‚ 692 โ€”
Python
avinashkranjan
avinashkranjan
Amazing-Python-Scripts

๐Ÿš€ Curated collection of Amazing Python scripts from Basics to Advance with automation task scripts.

Score
65
โ˜… 3.6k โ‘‚ 1.3k +4/day
Jupyter Notebook
ahmetoner
ahmetoner
whisper-asr-webservice

OpenAI Whisper ASR Webservice API

Score
100
โ˜… 3.3k โ‘‚ 580 +4/day
Python
shu223
shu223
iOS-10-Sampler

Code examples for new APIs of iOS 10.

Score
83
โ˜… 3.3k โ‘‚ 329 โ€”
Swift
pytorch
pytorch
audio

Data manipulation and transformation for audio signal processing, powered by PyTorch

Score
69
โ˜… 2.9k โ‘‚ 783 +3/day
Python
readbeyond
readbeyond
aeneas

aeneas is a Python/C library and a set of tools to automagically synchronize audio and text (aka forced alignment)

Score
50
โ˜… 2.8k โ‘‚ 276 โ€”
Python
linto-ai
linto-ai
whisper-timestamped

Multilingual Automatic Speech Recognition with word-level timestamps and confidence

Score
42
โ˜… 2.8k โ‘‚ 210 +1/day
Python
hahahumble
hahahumble
speechgpt

๐Ÿ’ฌ SpeechGPT is a web application that enables you to converse with ChatGPT.

Score
82
โ˜… 2.8k โ‘‚ 381 โ€”
TypeScript
pndurette
pndurette
gTTS

Python library and CLI tool to interface with Google Translate's text-to-speech API

Score
100
โ˜… 2.6k โ‘‚ 386 +1/day
Python
mravanelli
mravanelli
pytorch-kaldi

pytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding are performed with the kaldi toolkit.

Score
78
โ˜… 2.4k โ‘‚ 444 โ€”
Python
DigitalPhonetics
DigitalPhonetics
IMS-Toucan

Controllable and fast Text-to-Speech for over 7000 languages!

Score
95
โ˜… 2.2k โ‘‚ 317 โ€”
Python
travisvn
travisvn
openai-edge-tts

Free, high-quality text-to-speech API endpoint to replace OpenAI, Azure, or ElevenLabs

Score
76
โ˜… 2.0k โ‘‚ 299 +10/day
Python
Delta-ML
Delta-ML
delta

DELTA is a deep learning based natural language and speech processing platform. LF AI & DATA Projects: https://lfaidata.foundation/projects/delta/

Score
76
โ˜… 1.6k โ‘‚ 283 โ€”
Python
MiteshPuthran
MiteshPuthran
Speech-Emotion-Analyzer

The neural network model is capable of detecting five different male/female emotions from audio speeches. (Deep Learning, NLP, Python)

Score
35
โ˜… 1.4k โ‘‚ 435 โ€”
Jupyter Notebook
roatienza
roatienza
Deep-Learning-Experiments

Videos, notes and experiments to understand deep learning

Score
100
โ˜… 1.2k โ‘‚ 772 +1/day
Jupyter Notebook
lhotse-speech
lhotse-speech
lhotse

Tools for handling multimodal data in machine learning projects.

Score
97
โ˜… 1.1k โ‘‚ 277 โ€”
Python
nyrahealth
nyrahealth
CrisperWhisper

Verbatim Automatic Speech Recognition with improved word-level timestamps and filler detection

Score
19
โ˜… 962 โ‘‚ 54 โ€”
Python
EvelynFan
EvelynFan
FaceFormer

[CVPR 2022] FaceFormer: Speech-Driven 3D Facial Animation with Transformers

Score
27
โ˜… 914 โ‘‚ 147 โ€”
Python
FireRedTeam
FireRedTeam
FireRedTTS

An Open-Sourced LLM-empowered Foundation TTS System

Score
38
โ˜… 909 โ‘‚ 84 โ€”
Python
lmnt-com
lmnt-com
diffwave

DiffWave is a fast, high-quality neural vocoder and waveform synthesizer.

Score
65
โ˜… 886 โ‘‚ 131 โ€”
Python
yeyupiaoling
yeyupiaoling
PPASR

ๅŸบไบŽPaddlePaddleๅฎž็Žฐ็ซฏๅˆฐ็ซฏไธญๆ–‡่ฏญ้Ÿณ่ฏ†ๅˆซ๏ผŒไปŽๅ…ฅ้—จๅˆฐๅฎžๆˆ˜๏ผŒ่ถ…็ฎ€ๅ•็š„ๅ…ฅ้—จๆกˆไพ‹๏ผŒ่ถ…ๅฎž็”จ็š„ไผไธš้กน็›ฎใ€‚ๆ”ฏๆŒๅฝ“ๅ‰ๆœ€ๆต่กŒ็š„DeepSpeech2ใ€Conformerใ€Squeezeformerๆจกๅž‹

Score
84
โ˜… 873 โ‘‚ 130 โ€”
Python
santi-pdp
santi-pdp
segan

Speech Enhancement Generative Adversarial Network in TensorFlow

Score
70
โ˜… 861 โ‘‚ 280 โ€”
Python
TrevorS
TrevorS
voxtral-mini-realtime-rs

Voxtral ASR & TTS running natively and in the browser. A Rust implementation of Mistral's Voxtral mini realtime ASR / TTS using the Burn ML framework

Score
100
โ˜… 804 โ‘‚ 51 +5/day
Rust
AlphaAvatar
AlphaAvatar
AlphaAvatar

A real-time interactive Omni Avatar built on LiveKit, which allows you to seamlessly integrate with any open source Avatar components (real-time model, visual, voice, memory, search, etc.).

Score
94
โ˜… 799 โ‘‚ 58 +1/day
Python
vbelz
vbelz
Speech-enhancement

Deep learning for audio denoising

Score
59
โ˜… 764 โ‘‚ 131 โ€”
Python
cboard-org
cboard-org
cboard

Augmentative and Alternative Communication (AAC) system with text-to-speech for the browser

Score
100
โ˜… 740 โ‘‚ 278 โ€”
JavaScript
coqui-ai
coqui-ai
TTS-papers

๐Ÿธ collection of TTS papers

Score
54
โ˜… 731 โ‘‚ 79 โ€”
yeyupiaoling
yeyupiaoling
MASR

Pytorchๅฎž็Žฐ็š„ๆตๅผไธŽ้žๆตๅผ็š„่‡ชๅŠจ่ฏญ้Ÿณ่ฏ†ๅˆซๆก†ๆžถ๏ผŒๅŒๆ—ถๅ…ผๅฎนๅœจ็บฟๅ’Œ็ฆป็บฟ่ฏ†ๅˆซ๏ผŒ็›ฎๅ‰ๆ”ฏๆŒConformerใ€Squeezeformerใ€DeepSpeech2ๆจกๅž‹๏ผŒๆ”ฏๆŒๅคš็งๆ•ฐๆฎๅขžๅผบๆ–นๆณ•ใ€‚

Score
92
โ˜… 724 โ‘‚ 116 +1/day
Python
drethage
drethage
speech-denoising-wavenet

A neural network for end-to-end speech denoising

Score
57
โ˜… 706 โ‘‚ 160 โ€”
Python
Orenoid
Orenoid
BabelDuck

Beginner-friendly AI conversation practice application

Score
88
โ˜… 690 โ‘‚ 30 +1/day
TypeScript
googleapis
googleapis
nodejs-speech

This repository is deprecated. All of its content and history has been moved to googleapis/google-cloud-node.

Score
68
โ˜… 682 โ‘‚ 278 โ€”
daniilrobnikov
daniilrobnikov
vits2

VITS2: Improving Quality and Efficiency of Single-Stage Text-to-Speech with Adversarial Learning and Architecture Design

Score
51
โ˜… 641 โ‘‚ 73 โ€”
Jupyter Notebook
travisvn
travisvn
chatterbox-tts-api

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.)

Score
0
โ˜… 621 โ‘‚ 147 โ€”
Python
google
google
tacotron

Audio samples accompanying publications related to Tacotron, an end-to-end speech synthesis model.

Score
46
โ˜… 539 โ‘‚ 82 โ€”
HTML
yl4579
yl4579
StarGANv2-VC

StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversion

Score
49
โ˜… 521 โ‘‚ 110 โ€”
Python
Yuan-ManX
Yuan-ManX
audio-development-tools

Audio Development Tools (ADT) is a project for advancing sound, speech, and music technologies, featuring components for machine learning, sound synthesis, speech and music generation, signal processing, game audio, digital audio workstations (DAWs), and more.

Score
43
โ˜… 461 โ‘‚ 34 +1/day
marcogdepinto
marcogdepinto
emotion-classification-from-audio-files

Understanding emotions from audio files using neural networks and multiple datasets.

Score
15
โ˜… 433 โ‘‚ 141 โ€”
Python
ictnlp
ictnlp
Stream-Omni

Stream-Omni is a GPT-4o-like language-vision-speech chatbot that simultaneously supports interaction across various modality combinations.

Score
35
โ˜… 389 โ‘‚ 45 +1/day
Python
dusty-nv
dusty-nv
NanoLLM

Optimized local inference for LLMs with HuggingFace-like APIs for quantization, vision/language models, multimodal agents, speech, vector DB, and RAG.

Score
41
โ˜… 376 โ‘‚ 65 โ€”
Python
speechbrain
speechbrain
speechbrain.github.io

The SpeechBrain project aims to build a novel speech toolkit fully based on PyTorch. With SpeechBrain users can easily create speech processing systems, ranging from speech recognition (both HMM/DNN and end-to-end), speaker recognition, speech enhancement, speech separation, multi-microphone speech processing, and many others.

Score
41
โ˜… 373 โ‘‚ 31 โ€”
HTML
tincans-ai
tincans-ai
gazelle

Joint speech-language model - respond directly to audio!

Score
24
โ˜… 373 โ‘‚ 32 โ€”
Python
filippogiruzzi
filippogiruzzi
voice_activity_detection

Voice Activity Detection based on Deep Learning & TensorFlow

Score
81
โ˜… 372 โ‘‚ 69 โ€”
Python
primaryobjects
primaryobjects
voice-gender

Gender recognition by voice and speech analysis

Score
100
โ˜… 362 โ‘‚ 100 โ€”
R
Related Topics
#deep-learning#pytorch#tts#python#text-to-speech#machine-learning#ai#audio#speech-recognition#speech-synthesis#asr#speech-to-text

ยฉ 2026 GitRepoTrend ยท GitHub repositories by topic ยท Updated weekly