VoxCPM: Open Multilingual Text-to-Speech and Voice Design (GitHub, Scanned)
An open 2B text-to-speech model: 30 languages, voices from a description, and voice cloning.
Scanned 5 min read
Loading…
/** @github-tools */
Best Voice & Audio Tools on GitHub
These free tools transcribe speech, type what you say, edit recordings, read text aloud and even write music, mostly offline on your own machine. Good ones are actively maintained, run on ordinary hardware and are clear about what they need. Pick by the job: dictation, meeting notes, transcripts, audio editing, speech or DJ mixing. If a tool can copy a voice, only use it on your own voice or with clear permission.
19 repos, each cloned and scanned
// top 10, ranked
Updated 30 October 2026 · moves since 26 October 2026 · re-ranked every 3 days on what readers use, never sponsored
- 1
Buzz: Transcribe Audio Offline With Whisper (GitHub, Scanned)
up 3A friendly desktop app for transcribing and translating audio files offline, no command line needed.
- 2
Audacity: The Free Audio Editor, Now on Version 4 (GitHub, Scanned)
down 1The classic free audio editor and recorder, for anyone cleaning up podcasts, voiceovers or music.
- 3
whisper.cpp: Fast, Private Speech to Text (GitHub, Scanned)
down 1Runs Whisper speech recognition fast on a laptop with no Python, the best base for offline transcription.
- 4
Handy: Free Offline Dictation for Any App (GitHub, Scanned)
down 1Hold a key, speak and your words appear in any app, transcribed offline, great for dictation.
- 5
WhisperX: Fast Transcripts With Word Timestamps and Speaker Labels (GitHub, Scanned)
no changeFast Whisper transcripts with word timings and speaker labels, ideal for interviews and subtitles.
- 6
Meetily: Private AI Meeting Notes With No Bot (GitHub, Scanned)
no changeRecords, transcribes and summarises meetings on your own computer, with no bot joining the call.
- 7
VoxCPM: Open Multilingual Text-to-Speech and Voice Design (GitHub, Scanned)
no changeA capable open text to speech model in 30 languages; its voice cloning should only be used with the speaker's consent.
- 8
ACE-Step 1.5: Make Full Songs With Vocals Locally (GitHub, Scanned)
no changeWrites full songs with lyrics and vocals on your own GPU, the most practical open music generator here.
- 9
ebook2audiobook: Turn E-Books Into Audiobooks With Local AI (GitHub, Scanned)
no changeTurns EPUB, PDF and other ebooks into chaptered audiobooks with local text to speech.
- 10
Mixxx: Free Open-Source DJ Software (GitHub, Scanned)
no changeFree DJ software for live mixing with hundreds of supported controllers, built by a large, long running community.
// all 21 in Voice & Audio
CosyVoice: Open-Source Multilingual Text-to-Speech Models (GitHub, Scanned)
Open text-to-speech models that speak 9 languages and 18+ Chinese dialects, with streaming output.
Scanned 5 min read
Audacity: The Free Audio Editor, Now on Version 4 (GitHub, Scanned)
The free, open-source audio editor and recorder for Windows, macOS and Linux.
Scanned 3 min read
pyVideoTrans: Translate and Dub Videos into Another Language (GitHub, Scanned)
Transcribe a video, translate its subtitles and dub it in another language, locally or via cloud AI.
Scanned 5 min read
Kitten TTS: Realistic Text to Speech That Runs on a CPU (GitHub, Scanned)
Open text-to-speech models that run on a CPU, with 47 built-in voices and 20 languages.
Scanned 3 min read
YuE2: Open Song Generation With Vocals From Lyrics (GitHub, Scanned)
Generates full songs with vocals and accompaniment from lyrics and a style, with an editable score.
Scanned 3 min read
OpenWhispr: Private Voice Dictation for Any App (GitHub, Scanned)
Press a hotkey, speak, and your words appear at the cursor, with local or cloud speech models.
Scanned 6 min read
anarlog: Open-Source Granola Alternative for Meeting Notes (GitHub, Scanned)
An AI meeting notepad that records on your own device, with no bot joining the call.
Scanned 6 min read
Mixxx: Free Open-Source DJ Software (GitHub, Scanned)
Free DJ software for live mixing, with support for hundreds of controllers.
Scanned 3 min read
Kokoro-FastAPI: Local Text-to-Speech with an OpenAI-Style API (GitHub, Scanned)
Run the small Kokoro TTS model in Docker behind an OpenAI-compatible speech API, on CPU or GPU.
Scanned 4 min read
F5-TTS: Clone a Voice From a Few Seconds of Audio, Locally (GitHub, Scanned)
Open text-to-speech that copies a voice from a short clip, with a local web app and command line.
Scanned 3 min read
WhisperX: Fast Transcripts With Word Timestamps and Speaker Labels (GitHub, Scanned)
Whisper transcription up to 70x real time, with word-level timestamps and who-said-what labels.
Scanned 5 min read
GPT-SoVITS: Clone a Voice From One Minute of Audio, Locally (GitHub, Scanned)
Open-source voice cloning and text-to-speech that runs on your GPU, with a web interface.
Scanned 4 min read
ebook2audiobook: Turn E-Books Into Audiobooks With Local AI (GitHub, Scanned)
Converts EPUB, PDF, MOBI and other e-books into chaptered audiobooks with local text-to-speech.
Scanned 4 min read
VibeVoice: Microsoft's Open Speech Models for Long Audio (GitHub, Scanned)
Microsoft's open speech models: hour-long transcription with speaker labels and a realtime voice.
Scanned 3 min read
ACE-Step 1.5: Make Full Songs With Vocals Locally (GitHub, Scanned)
An open music model that writes full songs with lyrics and vocals on your own GPU, in seconds.
Scanned 7 min read
Handy: Free Offline Dictation for Any App (GitHub, Scanned)
Hold a shortcut, speak, and your words are typed into any app, transcribed offline on your machine.
Scanned 5 min read
Meetily: Private AI Meeting Notes With No Bot (GitHub, Scanned)
Records, transcribes and summarizes meetings on your own computer, with no bot joining the call.
Scanned 5 min read
Buzz: Transcribe Audio Offline With Whisper (GitHub, Scanned)
A desktop app that transcribes and translates audio and video offline with Whisper, no account needed.
Scanned 5 min read
// How we scan
Before a repository gets a post here we clone it and run the same checks on every one. The scanner is a script in this site's own repository, its findings are written out with file and line, and a person reads every hit before writing the verdict in the post. The last full run was on Oct 28, 2026.
- Pinned commit
- A fresh clone of the default branch. The commit and date are on every report, so the findings are about one snapshot, not the repository in general.
- Secrets
- Credential patterns with a known shape: cloud access keys, API tokens for OpenAI, Anthropic, Slack, GitHub, Google and Stripe, chat webhooks, private key blocks.
- Suspicious code
- Code that decodes a string and then executes it, pipes a download straight into a shell, opens a raw socket to a shell, reaches a known exfiltration service, mines cryptocurrency, or looks packed.
- Install-time code
- npm lifecycle scripts, setup.py command classes, Cargo build scripts, and installer shell scripts: whether they use sudo, edit your shell profile, or fetch and run remote code.
- Committed binaries
- Executables and compiled objects identified by their bytes, not their file extension, so a renamed binary still shows up.
- CI workflows
- GitHub Actions that run on pull_request_target and check out the pull request head (a classic way to leak secrets), write-all permissions, and third-party actions pinned to a tag instead of a commit.
- Network hosts
- Every host the source code talks to, so an unexpected one stands out.
- Known vulnerabilities
- Every pinned dependency in the repository's lockfiles looked up in OSV.dev, counted by severity. Includes development dependencies, which is why the counts are not zero for a large web app.
- Project hygiene
- A security policy, automated dependency updates, CodeQL, a licence, contributing guidelines.
- OpenSSF Scorecard
- The Open Source Security Foundation's independent score, where the project has one.
Safe means no credential patterns, no decode-and-execute code, no exfiltration hosts, no undocumented install-time behaviour, no risky workflow, and nothing in the findings a reviewer could not explain. Anything you should know before installing (an installer that pipes to a shell, a tool that reads a credential you already have, a licence with conditions, or a lockfile with unpatched advisories) is the note beside the badge.
Not covered: we do not run the software, audit its logic, or review commits made after the scan. The date and commit are on every report. Check them, and read the code yourself before you trust it with anything that matters.
// Questions
- Are these GitHub AI tools free to use?
- All of them are free to download, run and modify. The licences differ: most are MIT or Apache 2.0, ComfyUI is GPL-3.0, and Open WebUI and Dify ship their own licences with conditions on rebranding and multi-tenant hosting. Each post says which licence applies and what it asks of you.
- What does it mean that a repository was scanned?
- We cloned it at a specific commit and ran the checks listed under How we scan: credential patterns, decode-and-execute code, install-time scripts, committed binaries, risky CI workflows, every host the code talks to, known vulnerabilities in pinned dependencies, and project hygiene. Every hit was read by a person before the verdict was written, and the findings are in each post.
- Why do known vulnerabilities show up in a scan marked safe?
- Because a lockfile pins development dependencies too. A large web app carries thousands of packages and OSV knows of advisories in some of them; most affect build tooling and never reach a user. Each post shows the counts per lockfile and the worst entries so you can see where they sit, and the notes say whether any of it ships to you.
- How current is a scan?
- The date and commit are printed in every post. Active projects merge dozens of commits a week, so treat a report as a snapshot of that commit, not a standing guarantee, and re-check the repository before installing anything on a machine you care about.
- Which of these should I start with?
- To run a model on your own computer, install Ollama and add Open WebUI for a chat interface. For images and video, ComfyUI. To build an app or agent without much code, Dify. To let an agent write code or use a browser, OpenHands, Codex or browser-use. If you already use Claude Code or Codex, cost-xray shows what each session actually costs.