Get in touch
Get in touch
Open source

Changelog

Every project added, and every release, licence change, archive or move the weekly GitHub check noticed, by date. Subscribe to the feed at /open-source.xml.

October 26, 2026

  • AddedBetterWispr: A free, open-source dictation app for macOS under Apache-2.0 that holds a shortcut, listens, and pastes the text where your cursor is, with Whisper, NVIDIA Parakeet or Apple on-device speech recognition.
  • Addedhyprwhspr-rs: An MIT-licensed Rust rewrite of hyprwhspr, built as a background daemon that listens for Hyprland shortcuts, transcribes with whisper.cpp or Parakeet locally, or with Groq, Gemini or an OpenAI-compatible endpoint.
  • Addedmiii: An MIT-licensed terminal coding agent that plans, edits, runs and tests code with any model from 14 providers, including local Ollama, LM Studio, llama.cpp and vLLM.
  • AddedOpenFlow: An MIT-licensed desktop dictation app forked from Handy, with three independent backend modes for speech-to-text and AI cleanup, a wake-word mode and OS-keychain API keys.
  • AddedSafeTyper: An Apache-2.0 browser extension that checks grammar and spelling with a model you choose, running against OpenRouter, Groq or a local Ollama server, with keys stored in the extension.
  • Addedsayszz: An MIT-licensed on-device dictation app for macOS and Windows that tap-triggers Whisper, with Metal acceleration on Apple Silicon through MLX, a searchable local history and a setup wizard.
  • AddedSimpaudio: An MIT-licensed Windows text-to-speech studio that runs Piper and Kokoro locally for voice synthesis, Whisper for speech-to-text, with voice blending, a visual SSML editor and SRT export.
  • AddedUseAgent: An AGPL-3.0 workspace that runs Claude Code, Codex, OpenCode or Pi in isolated sandboxes you can self-host, with every tool call recorded in Postgres.

October 19, 2026

  • AddedAetheron: An MIT Perplexity-style answer engine on Next.js that rewrites your question, searches SearXNG with a DuckDuckGo fallback, pulls the top pages through the Jina Reader API, scores chunks locally without a vector database and streams a cited answer from Groq's Llama.
  • AddedCreable: An MIT Lovable-style AI app builder from Totalum: the chat, workspace, code editor and publish flow are MIT code, with the coding agent, sandboxes, databases, hosting and domains supplied by the Totalum API behind one key.
  • Addedkincode: An MIT Claude Code alternative written in Go: a single binary with 14 built-in tools, soul files that pick persona and provider, an approval gate, a build-after-edit loop, undo of the last turn, plan mode, named subagents and MCP server support.
  • AddedLexa: An MIT Grammarly-style tool for macOS that corrects grammar, rewrites tone, and translates selected text in any app, backed by OpenRouter, Groq, Cerebras, Gemini, Mistral, Ollama, LM Studio or your ChatGPT or Claude subscription.
  • AddedNodea: An MIT branching AI chat canvas built on Claude: every reply is a node you can fork from, so a conversation grows as a tree you can pan and zoom, with model routing, streaming, color-coded nodes, local search and semantic search.
  • AddedNogrammerly: An MIT desktop writing assistant for Mac and Windows that checks spelling, grammar and style across almost every app, with AI rewrites and tone shaping provided by Apple Intelligence on Mac and Phi Silica on Windows Copilot+ PCs, entirely on the device.
  • AddedOpen Vibe Coding: An MIT browser-based AI coding workspace with an editable chat agent, a Sandpack live preview, runtime diagnostics the agent reads to repair itself, and a Tauri option to package the project for desktop or mobile.
  • AddedProofKey: An MIT Grammarly-style Chrome extension that routes grammar fixes, rewrites and translations to Chrome's built-in Gemini Nano on your computer, or to any provider you choose with your own key, with no backend, no account and no telemetry.
  • AddedUsami: An MIT native menu-bar app for macOS: select text in any app, click a floating button, and improve, rephrase, shorten, translate or custom-edit it with your Claude Pro, Max, ChatGPT Plus or Pro subscription.

October 12, 2026

  • AddedJot: An Apache-2.0 macOS dictation app that calls Gemini 3.5 Transcribe with your own key, writes audio to disk from the first millisecond for crash safety, and inserts polished text at your cursor without an account.
  • AddedOpen Glean: An open-source AI workspace over Hydra DB that answers questions across your memories, files and connected apps with cited sources, built with Next.js and the Hydra DB SDK, under Apache-2.0.
  • AddedOpsiforce: An AGPL-3.0, self-hosted web platform that builds and runs AI-generated apps inside your own Kubernetes cluster, with per-project pods, persistent workspaces, HTTPS routes and multiple environments.

September 28, 2026

  • AddedGemType: A free, Apache-2.0 Grammarly alternative that runs as a browser extension, a Microsoft Word add-in and a desktop tray app, checking grammar with your own free Google Gemini API key.
  • AddedOpenCode X: A fork of opencode with 280+ commits under MIT, adding LLM-based tool-output compression, a three-tier context safety net, autonomous goals with an independent judge, and native compatibility with Claude Code hooks, plugins and skills.
  • AddedOrbit Editor: A beta open-source AI code editor for macOS under Apache-2.0, forked from Void Editor and VS Code, that runs AI agents on your codebase with any model, keeps checkpoints and change diffs, and supports MCP.
  • AddedVanta: A programmatic AI video engine built on Remotion under MIT, that wires 40+ open-source voice, avatar, caption, video, music and image projects into one local render pipeline.
  • AddedVoice Gecko: A free, MIT dictation desktop app that runs Parakeet, Moonshine or Whisper on your own machine, ships an installer for Windows today, and has an optional paid Support tier that unlocks no features.
  • AddedWhispree: A free, MIT dictation app for macOS that speaks into any prompt box on your Mac, uses Groq for speech and a Codex OAuth token for language-model cleanup, and can also run local Whisper and Qwen models.
  • Addedyap: A free, MIT push-to-talk dictation app for macOS, Windows and Linux that runs faster-whisper locally by default, learns your vocabulary, and can also send audio to Groq or an OpenAI-compatible endpoint.

September 17, 2026

  • AddedActivepieces: An MIT automation builder its README calls an open-source replacement for Zapier, with hundreds of TypeScript pieces that double as MCP servers, AI agents, human approval steps and a no-code builder.
  • AddedAnythingLLM: An MIT all-in-one AI app from Mintplex Labs for chatting with your documents with citations, running agents with MCP, and using any of 39 model providers including local llama.cpp and Ollama, as a desktop app or a multi-user Docker server.
  • AddedArize Phoenix: Arize's AI observability platform built on OpenTelemetry for tracing, evaluations, datasets, experiments and prompt management, under the Elastic License 2.0, which forbids offering it as a hosted service.
  • AddedAuK: Tencent Hunyuan's 1.5-billion-parameter speech foundation model under MIT for code and weights, covering zero-shot text to speech, speech editing, enhancement and separation through one natural-language instruction interface.
  • New pageBolt: Published the open-source alternatives to Bolt page.
  • AddedBreeze TTS 2: An open-weight bilingual English and Chinese text-to-speech model built for real-time interaction, with voice cloning, voice design and inline vocal events, whose weights and self-hosted outputs are non-commercial.
  • AddedChat UI: Hugging Face's Apache-2.0 chat interface, the code behind HuggingChat, that talks to any OpenAI-compatible API, stores chats in MongoDB, calls MCP tools, and can route each message to a model automatically.
  • AddedChatbox: The GPL-3.0 community edition of a desktop and mobile chat client for ChatGPT, Claude, Gemini and local Ollama models that keeps conversations on your device, with a separate pro edition synced from the same code.
  • New pageChatGPT: Published the open-source alternatives to ChatGPT page.
  • AddedChef: Convex's Apache-2.0 AI app builder, a fork of bolt.diy, that builds full-stack web apps with a built-in database, authentication, file uploads, real-time interfaces and background jobs on the Convex backend.
  • AddedCherry Studio: An AGPL-3.0 desktop client for Windows, macOS and Linux that connects OpenAI, Gemini, Anthropic and local Ollama or LM Studio models, with 300+ preset assistants, side-by-side model chats, file support and MCP servers.
  • New pageClaude: Published the open-source alternatives to Claude page.
  • New pageClaude Code: Published the open-source alternatives to Claude Code page.
  • AddedCline: An Apache-2.0 coding agent for VS Code, JetBrains, the terminal and a desktop app that edits files as reviewable diffs, runs commands with your approval, works with any model provider including Ollama, and connects tools through MCP.
  • AddedCodex CLI: OpenAI's Apache-2.0 coding agent that runs locally in your terminal, with a desktop app and IDE extensions, signed in with a ChatGPT plan or an OpenAI API key, so the code is open and the models are OpenAI's.
  • AddedComfyUI: The GPL-3.0 node-graph engine for image, video, audio and 3D generation that supports the newest open models, from Stable Diffusion and Flux to Wan and LTX video, on NVIDIA, AMD, Intel and Apple hardware, offline.
  • AddedCrush: Charm's terminal coding agent with 28 provider integrations, local models through llama.cpp, Ollama and LM Studio, MCP over three transports and permission prompts by default, under the Functional Source License, which becomes MIT two years after each release.
  • New pageCursor: Published the open-source alternatives to Cursor page.
  • New pageDevin: Published the open-source alternatives to Devin page.
  • AddedDify: An LLM app development platform with visual AI workflows, RAG pipelines, sandboxed agents, MCP tools and hundreds of models, under Apache-2.0 plus conditions that forbid multi-tenant use and removing the logo without permission.
  • AddedDyad: A local, open-source AI app builder for Mac and Windows that its README compares to Lovable, v0 and Bolt running on your own machine, with your own API keys and no sign-up, under Apache-2.0 apart from a fair-source pro directory.
  • AddedFluidVoice: A GPL-3.0 macOS dictation app that runs Nemotron, Parakeet, Cohere Transcribe, Apple Speech or Whisper on the device, with command and write modes, per-app prompts, and an optional closed local enhancement model.
  • AddedGemini CLI: Google's Apache-2.0 terminal agent for Gemini models with a free tier of 1,000 requests a day on a personal Google account, built-in search grounding, file and shell tools, MCP support, checkpointing and a GitHub Action.
  • New pageGitHub Copilot: Published the open-source alternatives to GitHub Copilot page.
  • New pageGlean: Published the open-source alternatives to Glean page.
  • Addedgoose: An Apache-2.0 general-purpose AI agent from the Agentic AI Foundation at the Linux Foundation, written in Rust, with a desktop app, a CLI and an API, 15+ model providers including Ollama, and 70+ extensions over MCP.
  • Addedgptme: An MIT personal AI agent for the terminal that runs shell and Python locally, patches files, browses the web, works with Anthropic, OpenAI, Google, xAI, DeepSeek, OpenRouter or a local llama.cpp server, and is both an MCP client and an MCP server.
  • New pageGrammarly: Published the open-source alternatives to Grammarly page.
  • AddedHarper: An Apache-2.0 English grammar checker from Automattic that lints a document in milliseconds, uses a fraction of LanguageTool's memory by its own measure, runs privately in your editor or in the browser through WebAssembly.
  • AddedHuginn: An MIT system, running since 2013, for building agents that watch the web and act for you, which its README calls a hackable version of IFTTT or Zapier on your own server, with webhooks, scraping and JavaScript steps.
  • AddedInvokeAI: An Apache-2.0 creative image tool with a unified canvas for inpainting and outpainting, node workflows, and support for 28 model families from Stable Diffusion to Flux and Qwen Image, run as a local web app.
  • AddedJan: An Apache-2.0 desktop app from Menlo Research that downloads and runs open models from Hugging Face on your own computer, connects to OpenAI, Anthropic and others when you want, serves a local OpenAI-compatible API, and supports MCP.
  • AddedKhoj: An AGPL-3.0 personal AI that answers from the web and your own documents with any local or hosted model, builds custom agents, sends scheduled research by email, and runs self-hosted or in its maintainers' cloud.
  • AddedKilo Code: An MIT coding agent for VS Code, JetBrains and the CLI with inline autocomplete, Code, Plan, Ask, Debug and Review modes, an MCP marketplace, access to 500+ models with no API key to start, and a hosted cloud agent.
  • AddedLangflow: An MIT visual platform for building and deploying AI agents and workflows that turns every flow into an API or an MCP server, with Python-editable components and multi-agent orchestration.
  • AddedLangfuse: An open-core LLM engineering platform, MIT outside its ee folders and part of ClickHouse since January 2026, for tracing, prompt management, evaluations, datasets and a playground, with Python and TypeScript SDKs.
  • New pageLangSmith: Published the open-source alternatives to LangSmith page.
  • AddedLanguageTool: An LGPL-2.1 proofreading engine for English, Spanish, French, German, Portuguese, Polish, Dutch and more than 20 other languages, which you can run as your own HTTP server with an API, or inside LibreOffice.
  • AddedLibreChat: An MIT self-hosted chat platform that puts Anthropic, OpenAI, Google, Bedrock, Azure, Ollama and any OpenAI-compatible model in one interface, with agents, MCP, a code sandbox, web search, artifacts and multi-user sign-in.
  • AddedLlama Coder: An MIT open-source take on Claude Artifacts that generates small apps from one prompt with Llama 3.1 405B on Together AI and previews them in a sandboxed in-browser renderer.
  • Addedllama.cpp: The MIT C and C++ inference engine behind much of local AI, running GGUF models with 1.5 to 8-bit quantisation on CPUs, Apple Silicon and 17 hardware backends, with an OpenAI-compatible server and a web interface built in.
  • AddedLobeHub: LobeHub, formerly LobeChat, is an agent workspace with an agent builder, agent groups, scheduled runs, editable memory and a library of over 10,000 tools and MCP plugins, under a community licence that needs a paid licence to distribute a modified version.
  • AddedLocalAI: An MIT engine that runs text, vision, voice, image and video models on any hardware, no GPU required, behind drop-in OpenAI, Anthropic and ElevenLabs-compatible APIs, over 60+ backends including llama.cpp, vLLM and whisper.cpp.
  • New pageLovable: Published the open-source alternatives to Lovable page.
  • AddedLTeX+ LS: Added LTeX+ LS: An MPL-2.0 language server that checks grammar and spelling in LaTeX, Markdown, Typst, AsciiDoc and 12 other markup formats with LanguageTool, in more than 20 languages, offline, with Java and LanguageTool bundled.
  • New pageMake: Published the open-source alternatives to Make page.
  • New pageMidjourney: Published the open-source alternatives to Midjourney page.
  • AddedMorphic: An Apache-2.0 AI search engine with a generative interface that answers with citations, using OpenAI, Anthropic, Google, Ollama or any OpenAI-compatible model and Tavily, SearXNG, Brave or Exa for search, with sign-in and shareable results.
  • Addedn8n: A fair-code workflow automation platform with 1,500+ integrations, 9,000+ templates, AI agents over OpenAI, Anthropic, Google or open models, and code steps in JavaScript and Python, under the Sustainable Use License.
  • AddedOllama: An MIT tool for downloading and running open models on your own machine with one command, built on llama.cpp, with a REST API, Python and JavaScript libraries, and a launcher that connects coding agents to local models.
  • AddedOnlook: An Apache-2.0 visual-first code editor for building Next.js and Tailwind sites and prototypes with AI, editing the page directly in the browser with a Figma-like interface while the code stays in sync.
  • AddedOnyx: An AI platform, formerly Danswer, that searches your company's knowledge through 50+ connectors with agentic retrieval, deep research, agents and actions, using any hosted or self-hosted model, with an MIT Community Edition.
  • AddedOpen WebUI: A self-hosted chat platform for Ollama and OpenAI-compatible models with document search over 9 vector databases, web search, image generation, roles and single sign-on, under a BSD-3 licence with an added branding clause.
  • AddedOpenCode: An MIT terminal coding agent with a full-access build agent and a read-only plan agent switched with the Tab key, installers for every platform, a beta desktop app, and the most-starred repository in this directory.
  • AddedOpenHands: An MIT self-hosted control centre, called Agent Canvas, that runs the OpenHands agent or Claude Code, Codex, Gemini and any ACP-compatible agent across local, Docker and cloud backends, with automations triggered by schedules and webhooks.
  • AddedOpik: Comet's Apache-2.0 LLM observability and evaluation platform, one licence across the whole repository, for agent tracing, LLM-as-a-judge evaluations, prompt management, production monitoring, CI tests and an MCP server.
  • New pagePerplexity: Published the open-source alternatives to Perplexity page.
  • AddedQwen Code: An Apache-2.0 coding agent from the Qwen team for the terminal, editor, desktop, browser and chat apps that works with OpenAI, Anthropic, Gemini and Qwen APIs or local models through Ollama and vLLM, switched at runtime, with MCP, a sandbox and subagents.
  • AddedSayIt: An AGPL-3.0 voice typing app for Windows that ships seven local speech models including Nemotron 3.5 ASR and three Qwen3-ASR sizes, with an editable AI cleanup step through Ollama or any OpenAI-compatible endpoint.
  • AddedSD.Next: An Apache-2.0 all-in-one web interface for AI image and video generation, descended from AUTOMATIC1111's WebUI, with LoRA, ControlNet, quantisation that cuts video memory up to four times, and the widest hardware list here.
  • AddedSpeakoFlow: An MIT desktop voice assistant for Windows, macOS and Linux that extends Handy's dictation core with a trigger phrase, a local cleanup model, screen-aware answers and Kokoro speech, with no account and no telemetry.
  • AddedSwarmUI: An MIT image and video generation web interface, formerly StableSwarmUI, with a simple Generate tab for beginners and a raw ComfyUI workflow tab for experts, that can spread work across several GPUs.
  • AddedTabby: A self-hosted coding assistant server with an Apache-2.0 core and a proprietary ee directory for the web server and team features, serving code completion and chat to VS Code, JetBrains and Vim from models on your own GPU.
  • AddedTextGen: An AGPL-3.0 desktop app for local models, formerly text-generation-webui, with five engines including llama.cpp and ExLlamaV3, an OpenAI and Anthropic-compatible API, tool calling, file chat, image generation and LoRA training, fully offline.
  • New pagethe OpenAI API: Published the open-source alternatives to the OpenAI API page.
  • Addedtwinny: An MIT VS Code extension for fill-in-the-middle code completion and sidebar chat that defaults to a local Ollama-compatible endpoint and works offline, with nine providers and no paid tier.
  • New pagev0: Published the open-source alternatives to v0 page.
  • AddedVale: An MIT command-line prose linter that turns a team's writing guidelines into checks that run in an editor, in CI and beside code, offline, understanding Markdown, AsciiDoc and code comments rather than plain text.
  • AddedVane: An MIT answer engine, formerly Perplexica, that searches the web through a bundled SearXNG and answers with cited sources, using local models through Ollama or hosted ones, in speed, balanced and quality modes, on your own hardware.
  • AddedvLLM: An Apache-2.0 engine from UC Berkeley's Sky Computing Lab for high-throughput model serving, with an OpenAI-compatible and Anthropic Messages API, 200+ model architectures, wide quantisation support, and parallelism across many GPUs.
  • AddedVoiceStudio: An AGPL-3.0 desktop workflow engine for voice cloning, voice design, video dubbing, dictation and audiobooks, running 16 speech engines and 10 transcription engines locally, with a local API and an MCP server for agents.
  • AddedWindmill: A developer platform for scripts, workflows, background jobs and internal UIs in Python, TypeScript, Go, Bash, SQL and more, AGPLv3 when built from source, with triggers from schedules, webhooks, Kafka and email.
  • New pageWindsurf: Published the open-source alternatives to Windsurf page.
  • AddedWriting Tools: A GPL-3.0 system-wide writing assistant for Windows, Linux and macOS that rewrites, proofreads or summarises selected text anywhere with one hotkey, using a local model through Ollama or a cloud model with your own key.
  • New pageZapier: Published the open-source alternatives to Zapier page.
  • AddedZed: A high-performance code editor from the creators of Atom and Tree-sitter, GPL-3.0-or-later with Apache-2.0 components, with an agent panel, external agents over ACP, edit prediction, MCP tools, sandboxing, and local models through Ollama or llama.cpp.

September 16, 2026

  • New pageAssemblyAI: Published the open-source alternatives to AssemblyAI page.
  • AddedBolna: An MIT voice-agent platform that defines an agent in a JSON file and orchestrates speech to text, a language model and text to speech over websockets, with Twilio and Plivo for phone calls, whose maintainers say they are looking for help.
  • AddedBuzz: A desktop app under MIT that transcribes and translates audio and video files, YouTube links and a live microphone offline with Whisper, with speaker identification and SRT, VTT and TXT export.
  • AddedChatterbox: A family of text-to-speech models from Resemble AI under MIT, with zero-shot voice cloning from a reference clip and a multilingual model covering 23 languages.
  • New pageDeepgram: Published the open-source alternatives to Deepgram page.
  • New pageElevenLabs: Published the open-source alternatives to ElevenLabs page.
  • New pageElevenLabs Agents: Published the open-source alternatives to ElevenLabs Agents page.
  • AddedF5-TTS: A research text-to-speech model with zero-shot voice cloning whose code is MIT but whose pretrained weights are non-commercial, because of the dataset they were trained on.
  • New pageFireflies.ai: Published the open-source alternatives to Fireflies.ai page.
  • AddedFish Speech: A multilingual text-to-speech system with voice cloning from a 10 to 30 second clip and inline emotion tags, released with its weights under a research licence that requires a separate agreement for commercial use.
  • AddedHandy: A free, offline push-to-talk dictation app for macOS, Windows and Linux that runs Whisper or NVIDIA Parakeet on your own machine and pastes the text at your cursor, under MIT.
  • AddedKokoro FastAPI: A Docker image that serves the 82-million-parameter Kokoro model through an OpenAI-compatible speech endpoint, with streaming, voice mixing and nine languages, all under Apache-2.0.
  • AddedLiveKit Agents: An Apache-2.0 framework for real-time voice agents that connects any speech, language and voice provider, with semantic turn detection, native MCP tool support, a test framework, and an open-source media and SIP stack it can run on entirely.
  • AddedMeetily: A meeting assistant under MIT that records your microphone and system audio together, transcribes live on your machine with Whisper or Parakeet, and summarises with a language model you choose.
  • AddedMoonshine: An on-device speech toolkit under MIT built for live streaming, with speech-to-text models trained from scratch in sizes down to 1 MB, one library across Python, the browser, phones and desktops.
  • AddedOpenWhispr: A dictation and meeting-notes app under MIT that runs Whisper or Parakeet locally or cloud models with your own key, detects Zoom, Teams and FaceTime calls, and labels speakers on device.
  • New pageOtter.ai: Published the open-source alternatives to Otter.ai page.
  • AddedParakeet (NeMo Speech): Added Parakeet (NeMo Speech): NVIDIA's speech models and toolkit: Apache-2.0 code, and the Parakeet TDT 0.6B v3 model under CC-BY-4.0 with 25 European languages, automatic language detection, punctuation and word timestamps.
  • AddedPipecat: A Python framework under BSD-2-Clause, maintained by Daily, for real-time voice and multimodal agents, with the widest provider list on this site and telephony serialisers for Twilio, Telnyx, Plivo, Vonage, Exotel and Genesys.
  • AddedPiper: A fast, local neural text-to-speech engine maintained by the Open Home Foundation, used by Home Assistant and the NVDA screen reader, under GPL-3.0.
  • New pageRetell AI: Published the open-source alternatives to Retell AI page.
  • Addedsherpa-onnx: A runtime under Apache-2.0 from the next-generation Kaldi team that runs speech to text, text to speech, speaker diarization and voice activity detection locally on CPUs, NPUs and phones, with no internet connection.
  • AddedSpeaches: An OpenAI-compatible server under MIT for streaming transcription, translation and text to speech, loading Whisper, Kokoro and Piper models on demand, described by its maintainers as Ollama for speech models.
  • New pageSuperwhisper: Published the open-source alternatives to Superwhisper page.
  • AddedTEN Framework: A real-time conversational AI framework from Agora with a visual designer, a SIP extension and turn detection, released under Apache-2.0 plus conditions that forbid competing deployments, which makes it source available rather than open source.
  • New pageVapi: Published the open-source alternatives to Vapi page.
  • AddedVibe: An offline transcription app under MIT that records system audio and the microphone, supports Whisper, Parakeet and Nemotron models, labels speakers, and exports SRT, VTT, TXT, HTML, PDF, JSON and DOCX.
  • AddedVoiceInk: A macOS dictation app under GPL-3.0 whose README names Superwhisper and Wispr Flow as the tools it replaces, with local models, per-app modes, a personal dictionary and an AI assistant mode.
  • AddedVosk: An offline speech recognition toolkit under Apache-2.0 with streaming, models of about 50 MB, 20+ languages, a reconfigurable vocabulary and speaker identification, from small boards to clusters.
  • AddedWhisper: OpenAI's general-purpose speech recognition model, released with code and weights under MIT, in six sizes from 39 million to 1.55 billion parameters, with multilingual transcription, translation to English and language detection.
  • Addedwhisper.cpp: A dependency-free C and C++ port of Whisper under MIT that runs on CPUs, Apple Silicon and phones, with quantised models, an HTTP server and bindings for a dozen languages.
  • AddedWhispering: A speech-to-text app inside the Epicenter monorepo under AGPL-3.0 that records, transcribes with a provider you choose, cloud or local, optionally polishes the text, and pastes it at the cursor.
  • AddedWhisperX: Batched Whisper transcription under BSD-2-Clause with word-level timestamps from forced alignment and speaker labels from pyannote, the closest open-source match to a hosted transcription API's output.
  • New pageWispr Flow: Published the open-source alternatives to Wispr Flow page.

Paying for an AI tool you would rather own?

Reveneau sets up the replacement on your own servers, connects it to your product, and builds the software around it.

Tell us what you run todayHow we do this work
Start a project