Open-source, fully local voice AI studio for macOS, Windows and Linux — voice cloning, voice design, dubbing, dictation and transcription in 646 languages.
Transcription
Converts speech to accurate text, with speakers labelled and timestamps you can jump straight to.
40 apps, 2 skills and 5 MCP servers tagged Transcription.
Apps
Local-first meeting and interview recorder that transcribes, labels speakers and writes up your notes entirely on your own computer, for a one-time price.
Free, fully on-device voice loop for AI coding agents — talk to Claude Code, Cursor or Codex and hear them answer back out loud.
Local-first AI memory for your media: index terabytes of video, audio and documents on your own machine and search them in plain language.
Voice dictation that works in every app and cleans up as you speak — no filler words, correct formatting, right tone.
AI note-taker for real-world conversations — pairs recorder hardware and a desktop capture app with transcription in 112 languages and template-driven summaries.
A wearable pendant and app that captures your conversations and turns them into a searchable personal memory.
Hit record, and Voicenotes transcribes, summarises and indexes what you said — then answers questions about anything you have ever recorded.
Searches the text, speech and faces inside your phone's photos and videos, with every model running on-device — no cloud, no account.
Real-time AI meeting assistant for Mac, Windows and iPhone that transcribes as you talk, answers questions mid-conversation and writes the notes afterwards.
Free AI audio and video transcription with timestamps, captions, and subtitle translation.
Handwriting-first notes, PDF annotation, whiteboards and text documents in one app, with AI transcription, summarisation and meeting notes layered on top.
AI meeting notetaker built to feed other AI tools: enriched transcripts with speaker and cross-meeting context, exportable to Claude or ChatGPT in one click.
AI notetaker that turns a recorded meeting into the deliverable it was about — slides, briefs, spreadsheets and images, not just a summary.
A router for voice models: 56 speech and language models benchmarked across 10 languages, with each session sent to the one that actually wins.
Open-source call intelligence that scores sales calls against your own playbook and the buyer's context, not just what the rep said.
One API for meeting bots across Zoom, Google Meet, Teams and Webex — join, record, stream and speak in real time, billed at $0.35 an hour.
AI note taker that records any Mac or iPhone audio and transcribes it on-device — no meeting bot, unlimited local transcription for free.
Local-first Mac dictation that types into any app, plus file and link transcription across 110 spoken languages on Apple Silicon.
Meeting recorder and note-taker with timestamped highlights and CRM sync, built for sales and customer teams.
Privacy-first voice to text for macOS, Windows, and iOS — runs offline on-device with customisable AI modes.
An AI medical scribe individual clinicians can start using today — notes, letters, and documents from any consult.
An AI scribe built by and for individual clinicians — SOAP notes in your own style, minutes after the visit.
An ambient AI assistant for clinicians that drafts notes and orders, designed around restoring eye contact with patients.
Ambient AI that listens to clinical conversations and writes the note, mapped to codes and linked to the audio.
Turn lectures, PDFs, and videos into structured notes, flashcards, and practice quizzes automatically.
Revenue intelligence built on every customer conversation — what was said, what it predicts, and what to do next.
Meeting notes precise enough to trust, with action items that automatically become tasks in your other tools.
A meeting assistant that joins calls, writes the notes, and measures engagement across meetings, email, and messages.
Speech-to-text APIs with built-in understanding — transcription plus summaries, topics, and redaction in one call.
Enterprise speech infrastructure — fast, accurate transcription, text to speech, and a full voice agent API.
Ultra-low-latency speech models built for real-time voice agents, where every millisecond is audible.
Fast, styled captions and automatic b-roll for short-form video — the editing polish, minus the editor.
An AI meeting assistant that records, transcribes, and summarizes calls with action items and CRM sync.
Fireflies records, transcribes, and summarizes meetings.
Otter transcribes meetings with AI and generates notes.
AI Companion helps with meetings, recaps, and compose.
VEED is an online video editor enhanced by AI.
Granola is an AI notepad designed for people who have back-to-back meetings.
Edit video and podcasts by editing text — Descript transcribes your recording so you can cut, rearrange, and polish media as easily as a document.
Skills
Skill: VideoDB
by VideoDB
VideoDB's official skill giving an agent one interface to ingest, index, search and edit video — including live RTSP feeds and real-time desktop capture.
NVIDIA's official skill for deploying and operating Nemotron Speech (Riva) NIMs — ASR, text-to-speech and translation, cloud-hosted or self-hosted on your own GPUs.
MCP servers
Fireflies.ai's official remote MCP server — 19 tools for searching meeting transcripts and summaries, pulling action items and analytics, and cutting soundbites from recorded calls.
ElevenLabs' official MCP server — generate speech, clone voices, transcribe audio, and build voice agents.
Local speech MCP server bundled with VoiceStudio — generate speech, clone a voice from reference audio, and transcribe in 646 languages, all on your own machine with no API key.
MCP: Deepgram
by Deepgram
Deepgram's official MCP server, bringing speech-to-text, text-to-speech and audio intelligence into Claude Code, Cursor and Windsurf.

MCP: MeetStream MCP Server
by MeetStream AI
Send a bot into a Zoom, Google Meet or Teams call from your agent: 19 tools covering the bot lifecycle, transcripts, per-participant media, live chat and calendar scheduling.
Related tags
Tags that appear alongside this one, ranked by how often.
