What is voice-pro built with?

Q: Which repos have a stack like voice-pro's?

The ones that share most of its stack: debpalash/VoiceStudio, jianchang512/pyvideotrans, and mudler/LocalAI.

voice-pro is a Python repo built with Lightning. It signs people in with browser-cookie3, uses AI through conformer, diffusers, evaluate, jiwer, misaki, and 15 more, makes its content with ffmpeg-python, markdown, torchcodec, and yt-dlp, deploys with structlog, and uses Hugging Face. It has 40,077 written lines.

Read on November 10, 2026, at commit 7231384. Read it as markdown

Frontend

Interface 3

Backend

Sign-in 1

browser-cookie3

AI 20

librosa8 files
ModelScope1 file
diffusers
evaluate
openai-whisper
onnxruntime5 files
pyworld3 files
f5-tts2 files
transformers2 files
x-transformers2 files
azure-ai-translation-text1 file
azure-cognitiveservices-speech1 file

8 more

demucs1 file
edge-tts1 file
faster-whisper1 file
kokoro1 file
wetext1 file
conformer
jiwer
misaki

Services 1

Hugging Face2 files · app/abus_hf_file.py, line 6

Support

The base 1

Lightning

Content 4

yt-dlp1 file
ffmpeg-python
markdown
torchcodec

Deploy 1

structlog54 files

Tools 1

Numba

Other 19

NumPy33 files
tqdm8 files
pyyaml6 files
cached-path1 file
websockets
pydub9 files
soundfile6 files
json55 files
hyperpyyaml4 files
deep-translator1 file
inflect1 file
python-dotenv1 file

7 more

soundcard1 file
gdown
more-itertools
py-cpuinfo
python-iso639
websocket-client
wget

Other repos with a similar stack

Ordered by how much of its stack they share with voice-pro, then by stars.

debpalashVoiceStudio
105.3k
VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.
15 of 51 in commonCompare →
jianchang512pyvideotrans
19.6k
Translate the video from one language to another and embed dubbing & subtitles.
14 of 51 in commonCompare →
mudlerLocalAI
50.3k
LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
13 of 51 in common · GoCompare →
ray-projectray
44.2k
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
12 of 51 in commonCompare →
RVC-BossGPT-SoVITS
64.6k
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
11 of 51 in commonCompare →
bojieliai-agent-book
57.6k
《深入理解 AI Agent：设计原理与工程实践》（李博杰著）开源主仓库：全书正文、编译版 PDF 与按章配套代码
10 of 51 in commonCompare →

Frequently asked questions

What language is voice-pro written in?

voice-pro is written in Python, with 40,077 written lines.

What framework does voice-pro use?

voice-pro is built with Lightning.

What does voice-pro sign people in with?

voice-pro signs people in with browser-cookie3.

Does voice-pro use AI?

Yes. voice-pro uses AI through conformer, diffusers, evaluate, jiwer, misaki, openai-whisper, librosa, onnxruntime, pyworld, f5-tts, transformers, x-transformers, azure-ai-translation-text, azure-cognitiveservices-speech, demucs, edge-tts, faster-whisper, kokoro, ModelScope, and wetext.

What services does voice-pro use?

voice-pro uses Hugging Face.

The proof: app/abus_hf_file.py, line 6

Which repos have a stack like voice-pro's?

The ones that share most of its stack:debpalash/VoiceStudio jianchang512/pyvideotrans mudler/LocalAI