whosaid MCP server

whosaid

<!-- mcp-name: io.github.sblattj/whosaid -->

Local, speaker-attributed transcription for Apple Silicon — who said what, on your Mac, nothing leaves the machine.

whosaid pairs Whisper speech-to-text with speaker diarization to turn a meeting, interview, call, or podcast recording into a transcript that says who spoke when — running fully offline and on-device on an Apple Silicon Mac, with no cloud service, no API keys, and no Hugging Face token. Think of it as whisper + speaker labels + voice-based speaker recognition, in one command.

Example output (meeting.speakers.txt):

[00:00:04] Alice: Thanks for jumping on, I know it's late for you.
[00:00:11] SPEAKER_01: No problem at all, happy to make it work.
[00:00:19] Alice: Let's start with the roadmap for next quarter.
[00:00:27] SPEAKER_01: Sounds good, I've got a few updates on that.

Why whosaid

person, not just a wall of text.

• Meetings, interviews, calls, podcasts — get a transcript where every turn is attributed to a

cloud step is one you opt into: [summarizer] engine = "claude" sends each transcript's text to Anthropic to draft action items. Leave it unset and nothing is sent.

• Privacy by construction — audio, text, and voice embeddings never leave your Mac. The only

your turns read as your name instead of SPEAKER_00.

• Your name on your own lines — a one-time ~45s voice enrollment teaches whosaid your voice, so

reported up front, with per-speaker turn counts and talk time.

• Tells you how many people spoke — the number of distinct speakers is auto-detected and

most representative snippets, so you can read a few lines and know who was talking.

• Speaker cards to identify who's who — for every speaker, whosaid writes a card of that voice's

voiceprint is saved to a private local registry so they're auto-named in every future transcript.

• Remembers people you name — identify a speaker once with whosaid relabel, and their

stitched back into consistent speakers by voiceprint, so an 80-minute meeting is minutes, not tens of minutes, recovering the same speakers as a single-pass run.

• Fast on long recordings — recordings over ~15 min are diarized in parallel windows and

source.

• No accounts, no API keys, no Hugging Face token — every model comes from an open, ungated

with Ollama, meaning) index over every transcript in a meeting workspace; whosaid search finds the turn, whosaid context shows the minute around it, and whosaid graph answers who committed to what, when. See Search your meetings.

• Search everything you have recorded. whosaid index builds a local full-text (and,

Memos folder (or any folder): stop recording, and a few minutes later the meeting is transcribed, summarized, and searchable. See Hands-free ingest.

• Hands-free from Voice Memos. whosaid watch install puts a launchd agent on the Voice

read-only workspace search tools as MCP tools for Claude Code, Claude Desktop, Kiro, and other MCP clients, with the same local-only guarantee as the CLI.

• Usable from an AI agent, too. whosaid mcp exposes transcribe, relabel, doctor, and the

How it compares

Looking for a MacWhisper, whisperX, or aTrain alternative? If you want speaker-attributed transcription that runs fully offline on Apple Silicon and can put real names on voices — not just SPEAKER_00 labels — that's the gap whosaid fills. Here's how it stacks up:

Shortened. The full README is on GitHub.