Audio
dograh
Open source voice AI platform. Self-hosted alternative to Vapi and Retell. On Prem, BYOK across Speech to Speech or LLM/STT/TTS, with a visual workflow build…
★ 5.8k starsBSD-2-Clause
View guide →// audio · librosa/librosa
librosa
librosa is an open-source audio project by librosa (librosa/librosa on GitHub). It has 8,647 GitHub stars and 1,080 forks, is released under the ISC license, and was last updated on GitHub on 29 September 2026.
Python library for audio and music analysis
★ 8.6k stars⑂ 1.1k forksISCupdated 2026-09
▦ visual — this project's README ships no embeddable screenshot,
so here's a placeholder. The guide below is complete regardless.
so here's a placeholder. The guide below is complete regardless.
// project facts
Project facts
- Repository
- librosa/librosa
- GitHub stars
- 8,647
- Forks
- 1,080
- License
- ISC
- Last updated on GitHub
- 29 September 2026
- Category
- Audio
- Listing
- Full install guide
- Official site
- Official site
// how it works
How it works
- Pick the job
Transcription, synthesis, voice changing, or editing — each tool here majors in one.
- Install and set up
Binaries, pip packages, or Docker; models download on first run for AI tools.
- Feed it audio or text
Drop in a recording or type what you want spoken.
- Export the result
WAV/MP3/OGG outputs drop straight into editors or apps.
// features
Why people love it
Audio-focused
Purpose-built for audio work with format support that just works.
Made for music
Workflows tuned for musicians and producers, not generic audio.
State-of-the-art models
Whisper-grade transcription and natural neural voices, free.
Offline capable
Many run fully on-device — nothing you say leaves the machine.
Free for products
Open licenses let you ship voice features without per-minute API bills.
Scriptable
CLI and Python APIs slot into larger pipelines.
Advertisement
// run it
Run it yourself
- Step 1 — Clone the repo
Download the source and move into the project folder.
git clone https://github.com/librosa/librosa.git cd librosa - Step 2 — Check the README
Every project documents its own setup; start with install requirements.
cat README.md | head -60 - Step 3 — Run it
Follow the project's launch command — Docker, pip, npm, or a binary release.
# see README for the exact launch command
// use cases
What you can build
- Transcribe meetings, lectures, and interviews.
- Generate voiceovers without a studio.
- Clone voices for dubbing and accessibility.
- Clean up and edit recordings.
Advertisement
// faq
Questions, answered
Who maintains librosa?
It is an open-source project at librosa/librosa with 1,080 forks. Check the repo's contributors and recent commits to see how active maintenance is.
Is librosa free for commercial use?
Licensed under ISC — check the repo for commercial-use terms.
Does it work offline?
Most of these run fully offline after the model download.
Can I use the voices commercially?
Check each license — many allow it, but voice-cloning has ethical and legal boundaries.
How accurate is the transcription?
Whisper-class models rival paid services on clear audio; noisy recordings need cleanup first.
// keep exploring
Similar tools
Audio
Retrieval-based-Voice-Conversion-WebUI
Easily train a good VC model with voice data <= 10 mins!
★ 38.6k starsMIT
View guide →Audio
leon
🧠 Leon is your open-source personal assistant.
★ 17.6k starsMIT
View guide →Audio
bark
Suno's text-prompted generative audio model: speech, music and sound effects from text prompts
★ 39.3k starsMIT
View guide →Audio
fastrtc
FastRTC turns any Python function into a real-time audio or video stream over WebRTC or WebSockets
★ 4.6k starsMIT
View guide →Audio
audio.cpp
A pure C++ ggml inference engine for audio models — TTS, STT, VAD, voice conversion and music.
★ 3.4k starsNOASSERTION
View guide →// alternatives
Alternatives in Audio
The most-starred other Audio projects in the LibreAI catalogue — the realistic shortlist if librosa is not the right fit.
- MoneyPrinterTurbo★ 128.3k
利用 AI 大模型和自动化工作流，根据主题或关键词一键生成高清短视频。Generate HD short videos from a topic or keyword with an automated AI workflow.
- Whisper★ 109.9k
Robust Speech Recognition via Large-Scale Weak Supervision
- GPT-SoVITS★ 62.3k
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
- Real-Time-Voice-Cloning★ 60.2k
Clone a voice from 5 seconds of audio and generate arbitrary speech in real time
- whisper.cpp★ 54.1k
Port of OpenAI's Whisper model in C/C++
// more in audio
More in Audio
Nearby Audio projects in the catalogue, closest in stars to librosa — keep exploring the shelf either side of it.
- espnet★ 10.0k
End-to-End Speech Processing Toolkit
- EmotiVoice★ 8.5k
EmotiVoice 😊: a Multi-Voice and Prompt-Controlled TTS Engine
- RealtimeSTT★ 10.2k
A robust, efficient, low-latency speech-to-text library with advanced voice activity detection, wake word activation and instant transcription.
- vits★ 7.9k
VITS — the original end-to-end text-to-speech model: a conditional VAE with adversarial learning, in PyTorch.
- Mozilla TTS★ 10.2k
Mozilla's deep-learning text-to-speech library with Tacotron, Glow-TTS and neural vocoders.
- MeloTTS★ 7.7k
MeloTTS — multilingual text-to-speech for English, Spanish, French, Chinese, Japanese and Korean.
Get librosa
Free and open — grab the source, star the repo, and start creating.