Open-source toolsAudio & voice

17 match your filters — 17 of them answered our check today.

Watching this group for 20 days · how we check

This week7 new arrivals

A free open-source browser music lab that detects chords from audio and separates vocals from instrumentals, for musicians learning songs by ear.

Domain registered 6 months ago

FreeNo sign-upOpen source
What to know
How it works
AI chord recognition on MP3/WAV and stateless vocal/instrumental separation
Pricing
free, open source, no registration
Best for
musicians learning or transcribing songs

Watched for 6 days · last checked today

Details →

An open-source toolkit for building AI features — chat, RAG, speech, vision — that runs entirely in the browser with no servers and no data leaving the device. Built for developers.

Domain registered 7 months ago

Works offlineData stays with youOpen source
What to know
How it works
An open-source toolkit for running AI entirely in the browser: LLM chat across 76 models, RAG and vector search, Whisper and Kokoro speech, and vision, with no server or API key required. Runs on WebGPU with a WebAssembly fallback.
What's different
Data never leaves the device, and it ships a zero-dependency core plus a shadcn UI registry of 107 components and 36 installable blocks for building on top of it.
Pricing
Open source (MIT license).
Best for
Developers building browser-based AI features without standing up servers or managing API keys.

Watched for 12 days · last checked 1d ago

Details →

Free open-source Mac dictation app that types cleaned-up text into any app entirely on-device, no account needed.

FreeNo sign-upWorks offlineOpen source
What to know
How it works
Hold a key, speak, on-device model transcribes and cleans up fillers/self-corrections
What's different
100% on-device, no account or server required
Pricing
Free, MIT-licensed

Watched for 4 days · last checked today

Details →

An offline clinical assistant for homeopaths that maps patient symptoms to remedies using local, private AI models.

Works offlineOpen source
What to know
How it works
Uses local LLMs to repertorize cases and extract clinical rubrics from voice dictation and images
Pricing
Open source
Watch out
100% offline, no cloud data sharing

Watched for 6 days · last checked today

Details →

Humla

Live

A Mac app that records and transcribes meetings entirely on-device, no bot joins the call. Free and open source, with optional cloud or self-hosted sync for teams.

FreeWorks offlineOpen sourceNo tracking
What to know
How it works
Records mic and call audio directly through macOS with no bot joining the meeting, then transcribes, labels speakers, and writes a summary that fuses your notes with the transcript. Runs fully on-device using Whisper on Apple Silicon, or with your own AI key.
What's different
No bot joins the call, and it can run entirely on-device with local SQLite storage and no telemetry.
Pricing
Free and MIT-licensed, with optional paid team sync via Humla Cloud or self-hosting.
Best for
Mac users who want private, on-device meeting transcription without a bot joining their calls.

Watched for 13 days · last checked 7d ago

Details →

A free, open source, Descript alternative. Runs in-browser.

FreeWorks offlineOpen source
What to know
How it works
Videoyu transkript metnini düzenleyerek keser; tamamen tarayıcıda, yerelde ve çevrimdışı çalışır.
What's different
Descript'in ücretli/bulut modeline karşı yerel ve ücretsiz.

First seen today · last checked today

Details →

An on-device dictation, rewriting, translation and local AI agent tool for Apple Silicon Macs - free and open-source (MIT), with no cloud, no accounts, and MCP support.

FreeWorks offlineOpen source
What to know
How it works
Runs on-device dictation, rewriting, and translation using multiple transcription models (Parakeet, CTC, Nemotron, Qwen3-ASR), plus a local agent that plans and calls tools like Apple Notes, clipboard, files, and MCP.
What's different
Fully local processing with no cloud and no accounts, and lets you swap or customize any underlying model or prompt.
Pricing
Free and open-source (MIT license).
Best for
Apple Silicon Mac users who want dictation and an AI agent without sending data to the cloud.
Watch out
Requires Apple Silicon and macOS 26; some listed models (Gemma 4, Qwen3.6, Ornith 1.0) are described as coming next, not yet available.

Watched for 17 days · last checked 11d ago

Details →

An open-source, bring-your-own-key voice assistant for the desktop that you fully customize, model, skills, themes, aimed at builders willing to configure their own AI stack.

Open source
What to know
How it works
An open-source, bring-your-own-key voice assistant for the desktop that performs tasks on your behalf. The voice, model, UI, skills, tools and widgets are all customizable.
What's different
Fully open and customizable rather than a fixed hosted assistant — you supply your own API key and build your own skills and themes.
Best for
Builders comfortable configuring and extending their own AI voice assistant stack rather than using a closed hosted product.

Watched for 15 days · last checked 9d ago

Details →

Self-hosted Discord bot that records calls per speaker and turns them into transcripts, meeting notes, and action items, queryable in Discord or via MCP, for teams and developers wanting private, searchable meeting memory, instead of manual note-taking or cloud recorder services.

FreeOpen sourceSelf-hosted
What to know
How it works
Discord bot that records each speaker's audio track during calls, then generates named transcripts, meeting notes, decisions, and action items; queryable inside Discord or via an MCP-capable AI assistant. Self-hosted, AGPL open source.
Pricing
Free.

Watched for 11 days · last checked 8d ago

Details →

A free, open-source Windows app that auto-generates styled subtitles for your videos using offline Whisper or the cloud Groq API — aimed at YouTube Shorts, TikTok and Reels creators, not developers.

FreeWorks offlineOpen sourceCan export my data
What to know
How it works
A Windows desktop app that automatically transcribes videos into word-level subtitles using either offline OpenAI Whisper or the cloud-based Groq API, then burns captions into the video or exports as SRT/VTT.
What's different
Free and open-source, with styling presets built for YouTube Shorts, TikTok, and Instagram Reels formats.
Pricing
Free.
Best for
YouTube Shorts, TikTok, and Instagram Reels creators who need styled captions on their videos.
Watch out
Windows-only desktop app; cloud transcription option (Groq) requires sending video data off-device, unlike the offline Whisper option.

Watched for 17 days · last checked 2d ago

Details →

A free, open-source, on-device dictation app for Mac — hold a key, speak, text appears in any app. No cloud, no accounts, no tracking; a private alternative to Wispr Flow.

FreeNo sign-upWorks offlineOpen source
What to know
How it works
A voice dictation app for macOS: hold a key, speak, and the words appear in any app, running entirely on the Apple Neural Engine (every Mac since the M1, 2020).
What's different
No cloud, no tracking, no accounts and no weekly limits, positioned as a private, on-device alternative to Wispr Flow. Supports custom vocabulary for jargon, names and technical terms.
Pricing
Free and open-source.
Best for
Mac users who want fast voice dictation without their speech leaving the device.

Watched for 18 days · last checked 9d ago

Details →

A local, privacy-first app that uses one on-device Gemma model to capture, transcribe, search, and automate your screen and audio history.

Works offlineOpen sourceNo tracking
What to know
How it works
Uses one local Gemma model on-device for screen vision, audio transcription, chat, and reasoning; captures only when content changes and lets you search or chat with your screen history in plain English.
What's different
Compared against Microsoft Recall (needs $1000+ hardware) and Screenpipe (needs separate OCR + Whisper + external LLM) — this runs one local model for everything.
Pricing
MIT licensed, pip install.
Watch out
Requires a 4GB GPU to run.

Watched for 8 days · last checked today

Details →

Rekody

Live

Free on-device macOS dictation app that types text at the cursor via a hold-to-talk hotkey.

Domain registered 3 months ago

FreeNo sign-upWorks offlineOpen source
What to know
How it works
Hold Option + Space and speak, and text lands at your cursor in any app, with a personal dictionary that learns your words.
Pricing
Free.
Watch out
On-device by default, no account or subscription; the CLI is open source (MIT).

Watched for 3 days · last checked 3d ago

Details →

A voice-to-text app that transcribes on-device and optionally cleans up grammar with a user-chosen AI, positioned as a free alternative to Wispr Flow.

FreeWorks offlineOpen source
What to know
How it works
Transcribes speech on-device (Parakeet/Whisper/Cohere), then optionally uses a chosen AI (Gemini, OpenAI, OpenRouter or local Ollama) to remove filler words and fix grammar; API keys stay in the Keychain.
What's different
Positioned as a free alternative to Wispr Flow, fully offline if you skip the AI cleanup step.
Pricing
Free, open-source.
Best for
People wanting private voice-to-text across any app.

Watched for 3 days · last checked 1d ago

Details →

Self-hosted tool that turns videos, links, articles and notes into private AI podcasts with a custom host voice.

Open sourceSelf-hosted
What to know
How it works
Turns videos, links, articles, and notes into private AI podcasts with a custom host persona and voice, MCP support for agents, and pluggable sources.
Pricing
Self-hosted, open source (LGPL-3.0), Docker-ready.

Watched for 3 days · last checked 2d ago

Details →

WebVox

Live

Reads web articles, blogs and pages aloud in a clean, ad-free listening mode using Android's built-in text-to-speech. A general read-it-later/listen tool for anyone, not developer-specific despite the tag.

No sign-upOpen source
What to know
How it works
Converts web articles, blogs and pages into a clean reader-mode layout and reads them aloud using Android's built-in text-to-speech engine, stripping ads, popups and banners; users paste a URL or share directly from the browser to start.
Best for
Anyone on Android who wants to listen to web articles instead of reading them, not developers specifically despite the extraction-tool angle.

Watched for 18 days · last checked 2d ago

Details →

An MCP server that gives Claude/ChatGPT/Gemini direct access to SEC filings, earnings call transcripts, and congressional trading data, citing sources.

FreeOpen source
What to know
How it works
90 tools + REST API over 5,000+ US stocks: filings, self-captured earnings call transcripts, KPIs, insider/congress trades.
What's different
Cites every answer to the source filing and is built to refuse guessing.
Pricing
Free tier: 100 calls/day.
Best for
Developers building financial research tools or analysts using AI assistants for filings research.

Watched for 6 days · last checked 5d ago

Details →