Open-source tools for Voice & audio

Speech, music, transcription, podcasts and voice agents.

Choose a task such as transcription, synthesis or editing. Compare languages, local processing and the audio formats you can import and export.

49 projects

agentring mutonby · Apache-2.0
agentring lets an AI agent call your phone like a real call when it needs a decision or finishes a job, a voice AI talks you through it, and the agent gets the…
agents livekit · Apache-2.0
An open-source framework for building realtime voice AI agents that can listen, see video, and talk back, with built-in telephony, turn detection, and MCP tool support.
ai-promo-video-maker liyupi · MIT
Tell it your product's name or URL and this agent skill researches it, sketches a few visual styles for you to choose from, captures real 4K screenshots, cuts the edit…
airlink memoair-labs · MIT
Gives AI agents a seat in a live team workspace, with shared docs, sheets, slides, browser, desktop, and voice, so humans and agents collaborate in real time.
audio-studio-mcp kanaworksai-hue · MIT
An MCP server that lets Claude Code or any MCP client generate royalty-free background music and sound effects locally, using the Stable Audio 3 model on your own Mac…
backtalk jaredrhod · AGPL-3.0
backtalk lets you talk to your Claude Code agent out loud instead of typing, using free local speech models for both listening and responding.
claudemy assafkip · MIT
A free Claude Code skill that turns any topic you name into about 12 two-minute audio lessons, each backed by real cited web research, so you get a finishable course…
deer-flow bytedance · MIT
An open-source AI super-agent that researches a topic, writes and tests code, and produces finished deliverables like reports or podcasts, running on its own for…
earshot leonxlnx · MIT
Gives AI coding agents the ability to hear and judge sound: describe, match, synthesize, and review audio for the videos, games, and demos those agents build, running…
echomind nirbhay41120003 · MIT
A local-first assistant that transcribes your speech live and lets you ask a private RAG chatbot questions grounded in what you have actually said, entirely on your…
explainroo vincentsch · MIT
Explainroo lets your coding agent (Claude Code, Codex) turn a plain-text script into a narrated explainer video automatically, entirely on your own machine with no API…
frametell sitor-ai · AGPL-3.0
A local-first desktop app where an AI agent turns one sentence or a document into a narrated, illustrated explainer video you approve step by step.
hex anomalyco · MIT
Hex is a cross-platform app where you hold a key, speak, and it transcribes your voice into text and pastes it wherever your cursor is, fully on-device.
khan-explainer haiderfarooq3 · MIT
A free, local Claude Code skill that generates Khan-Academy-style explainer videos: a pen draws on a whiteboard while an AI voice narrates, no cloud API keys needed.
kilnframe erhanmeydan · Apache-2.0
A free Premiere Pro/DaVinci Resolve plugin that listens to what you say and generates matching animated inserts and music, rendered locally.
lampline c4rohan · Apache-2.0
Lets you build, test, and run open-source AI phone agents on your own machine for a fraction of the cost of managed platforms like Dialogflow CX.
linkedin-skills sergebulaev · MIT
A free, open-source bundle of 12 Claude Code and Codex skills that draft LinkedIn posts, comments, and profile rewrites in your own voice, strip out AI-sounding tells,…
ltx-2 lightricks · Apache-2.0
Inference and fine-tuning tools for an AI model that generates video with synchronized audio from a single package.
markitdown microsoft · MIT
Converts PDFs, Word, PowerPoint, Excel, images and audio into clean Markdown so the text is ready to feed into an LLM.
moneyprinterturbo harry0703 · MIT
Give it a topic or keyword and it automatically writes a script with an LLM, finds matching footage, generates subtitles and a voiceover, and assembles a finished HD…
nari-qwen3-tts nari-labs · Apache-2.0
Nari Labs open-sourced a high-performance serving engine for Qwen3-TTS that starts speaking in under 50 milliseconds and handles 10 simultaneous voice-generation…
no-ai-slop petergyang · MIT
A free skill that scans your writing for 20+ common AI-generated patterns (like it is not X it is Y) and removes them while preserving your own voice.
npctalk christos-antono · MIT
Open-source project that lets any game NPC talk back in a cloned AI voice, with an LLM writing the in-character reply live; built first for GTA V.
ods osmantic · Apache-2.0
Installs and connects everything needed to run AI locally so you get a private AI server without assembling the pieces by hand.
OG Converter dr-at0mic · GPL-3.0-or-later
Office workers can turn Word, Excel and PowerPoint files into PDFs, merge or split PDFs, and password-protect documents without uploading them to a website. Students…
oido lokutor-ai · GPL-3.0
A free, open-source speech recognizer that runs entirely on a $5 microchip instead of the cloud, transcribing English and Spanish speech in real time with…
openmaic thu-maic · MIT
Give it one prompt or your own notes, slides, audio or video, and it builds a full interactive course you can work through like a class, with an agent that plans the…
openmontage calesthio · AGPL-3.0
Turns your AI coding assistant into a full video production studio: describe what you want and it researches, scripts, generates assets, edits, and renders a finished…
openwhispr openwhispr · MIT
OpenWhispr is a free, open-source, privacy-first alternative to WisprFlow and Granola: press a hotkey, speak, and your words appear at your cursor, with fully offline…
personal_external_brain chenkanglin198904 · MIT
A local-first tool that turns your notes, PDFs, web pages and audio/video into a private knowledge graph, and is designed to say I do not know rather than guess.
PhoneInput dr-at0mic · GPL-3.0-or-later
People whose computer has no microphone or a poor one, such as desktop PCs or laptops with weak built-in mics. They can join calls, record voice-overs or stream with…
pitupitu klarluft · Apache-2.0
A small open-source Rust agent that lets you start, check on, and unblock your Claude Code or Codex coding sessions by voice from your phone, from anywhere.
ppt-master hugohe3 · MIT
ppt-master uses AI to turn a document or topic into a real, editable PowerPoint deck, complete with charts, animations, and narrated speaker notes.
qwen-audio-agent qwenaudio · Apache-2.0
Gives AI agents a real-time voice so they can talk with people the way a live phone or voice assistant would.
remiqora inikolax · MIT
It runs AI music generation entirely on your own machine, turning a text prompt into a track and letting you split stems and edit in a built-in multitrack studio.
showtime faviovazquez · MIT
Install it as a Claude Code / Codex / Cursor plugin, describe a video in one sentence, and your agent writes the shots, voiceover, captions and music, then renders the…
skills scenario-labs · MIT
A skill pack that lets any AI agent generate ready-to-use images, video, audio and 3D assets while keeping characters and brand style consistent, and even drive…
sourcelens msmahdinejad · MIT
SourceLens turns a folder of documents into a research workspace: ask questions and get cited answers, or have it generate a podcast, a PowerPoint, or a video from the…
sparky anisayari · MIT
A free, open-source private AI assistant for Windows that runs entirely offline: chat like ChatGPT, see images, generate pictures and videos with sound, search your own…
transformers huggingface · Apache-2.0
The open-source library that provides ready-to-use implementations of virtually every major AI model for text, vision, audio, and multimodal use, letting developers run…
universal-modder rehan-remade · MIT
Point an AI coding agent (Claude Code, Codex, Cursor, Gemini CLI) at a PC game you own and it mods it: finds the engine, reads the code, generates new art/3D/audio with…
unsloth unslothai · Apache-2.0
A free local app for running and training your own AI language and image models on your own machine.
vibevoice microsoft · MIT
Microsoft's open-source voice AI family: text-to-speech that generates up to 90 minutes of natural multi-speaker audio from a script, plus speech recognition that…
voicebox jamiepine · MIT
A local-first, open-source AI voice studio that lets anyone clone a voice, generate speech, and dictate into any app on their own machine.
voicemem xzf-thu · Apache-2.0
Gives voice assistants a persistent memory that tracks facts and emotional context across conversations, so the assistant gradually gets to know each user, at low…
voicestudio debpalash · AGPL-3.0
A free, fully-local alternative to ElevenLabs that clones voices, dubs video, and creates audiobooks and transcripts across 646 languages, all on your own machine.
voxcpm openbmb · Apache-2.0
An open-source AI model that generates natural, cloned voices in multiple languages without needing a text tokenizer step.
yogurt frigadehq · MIT
A free, open-source desktop app that records your meetings, transcribes them locally with whisper.cpp, and writes AI summaries with a local model, no bot added to the…
yue multimodal-art-projection · Apache-2.0
YuE2 is an open-source frontier music-generation model that can plan a song structurally, create zero-shot covers, and let an agent iteratively edit the result.