AnyTool
Your files never leave your device. All processing happens locally in your browser.

How do I transcribe a meeting and label who said what for free, privately?

Open AnyTool's Speaker-Labeled Transcription, drop in a meeting or interview recording, and it transcribes the speech with a self-hosted model and automatically groups it by speaker (diarization) so each line is tagged "Speaker 1", "Speaker 2" and so on. Edit speaker names and text, then export a labeled transcript or timed SRT. Everything runs in your browser — no upload, no account, no per-minute cap, no CDN.

  • Automatic speaker diarization — labels who said what
  • Edit and rename speakers, then export a labeled transcript or SRT
  • Great for meetings, interviews and podcasts
  • 100% in your browser — no upload, no account, no cap

What is

Speaker diarization (who said what)

Speaker diarization is the process of partitioning a transcript by speaker — answering "who spoke when" — so each segment of speech is attributed to a distinct speaker label. Combined with speech-to-text it produces a transcript where every line is tagged with a speaker. A client-side tool performs both transcription and diarization in the browser without uploading the recording.

Audio Tools

Related terms

speaker diarizationtranscriptionmeeting notesWhisperSRT

How to Transcribe with Speaker Labels

Transcribe and diarize a recording in your browser to see who said what.

3 minWeb browser
  1. 1

    Add the recording

    Drop in a meeting or interview file — it stays on your device.

  2. 2

    Transcribe and diarize

    The tool produces text and tags each line with a speaker label.

  3. 3

    Edit and export

    Rename speakers, then export a labeled transcript or SRT — nothing is uploaded.

Result: A speaker-labeled transcript and SRT

Frequently Asked Questions

Yes — it diarizes the audio and tags each line with a speaker.

The tool groups speech segments by voice and assigns Speaker 1, Speaker 2 and so on, which you can rename — ideal for meetings, interviews and podcasts.

No — transcription and diarization run entirely in your browser.

Unlike Otter or Fireflies, which upload meeting audio to the cloud and cap free minutes, AnyTool processes the recording on your own device with nothing uploaded.

Yes — export a speaker-labeled transcript and timed SRT subtitles.

You get a clean transcript with speaker tags plus an SRT file that keeps the speaker labels and timestamps for video and review tools.

Detailed Explanation

Methodology

How Speaker-Labeled Transcription Works

AnyTool transcribes and diarizes a recording entirely in the browser. A self-hosted Whisper ASR model (transformers.js on WebAssembly/WebGPU) converts speech to timestamped text, while local speaker diarization clusters the audio by voice to attribute each segment to a distinct speaker (Speaker 1, Speaker 2, …). The transcript is rendered with editable speaker labels and timings, and can be exported as a labeled transcript or as SRT that preserves speaker tags. All audio is decoded with the Web Audio API and processed on the device — nothing is uploaded and no CDN inference is used.

  • Runs client-side — meeting audio is never uploaded
  • Self-hosted Whisper ASR for the transcript
  • Local speaker diarization groups speech by voice
  • Editable, renameable speaker labels
  • Export a labeled transcript and timed SRT
  • No per-minute cap, account or CDN inference
Privacy & Security

Privacy vs Cloud Meeting Transcribers

Otter, Fireflies, Fathom and tl;dv upload meeting recordings to the cloud, often join calls as a bot, cap free minutes and store transcripts on their servers. AnyTool performs both transcription and speaker diarization on the user's own device, so the recording never leaves the browser and there is no per-minute limit, watermark or sign-up. This makes it a private way to get "who said what" notes from sensitive meetings, interviews and podcasts.

Speaker transcription: AnyTool vs typical tools
CapabilityAnyToolTypical tools
Data handlingIn your browserUploaded to cloud
Speaker labelsYes (local diarization)Cloud-only
Per-minute capNoneCommon
ExportLabeled transcript + SRTVaries
Account requiredNoUsually

AnyTool is a privacy-first client-side transcriber — transcription and diarization run locally and nothing is uploaded.