Skip to content
Transcribr
Start free

Features

From recording to something you can use

Accurate transcription when you upload. When the work should stay put: capture a meeting tab as notes, convert and compress media, cut clips, fix captions against the audio, and redact before sharing — all in the browser.

Transcription

Speed or accuracy — you choose

Pick Quick for drafts, Standard for everyday meetings, or Premium when every word and speaker label matters. Upload MP3, MP4, YouTube links, or other audio/video sources.

  • Quick, Standard, and Premium modes
  • Works with audio files, video, and YouTube URLs
  • Clear accuracy and time estimates per tier

Select Transcription Type

Quick
Time ~2 minsAccuracy Standard
Basic transcriptionStandard timestamps
StandardPopular
Time ~5 minsAccuracy High
Enhanced accuracySpeaker detection
Premium
Time ~12 minsAccuracy Highest
Highest accuracySpeaker identification

Processing pipeline

See every step as it happens

From fetching your media to language detection, speech-to-text, speaker identification, and finalising — Transcribr shows live progress so you never wonder what's happening.

  • Live step-by-step progress checklist
  • Detect errors early and retry if needed
  • Track all jobs from your dashboard

Your transcription is being processed

This usually takes a few minutes. You can close this screen — we'll notify you when it's done.

Progress57%
  • Fetching media
  • Audio extraction
  • Language detection
  • Speech-to-text
  • Speaker identification
  • Timestamp alignment
  • Finalising

Summarisation & insights

Turn raw transcripts into actionable notes

Every completed transcript comes with a quick summary plus an executive summary that breaks down key topics with explanations, decisions and findings, and actionable takeaways — ideal for meetings, interviews, and court notes.

  • Quick summary for instant context
  • Executive summary: overview, key topics, decisions, takeaways
  • Identifies participants and follow-up items
  • Save or share the summary as a PDF

00:00 – 01:15

Jesse Makanaki ▾Renamed

Good morning, everyone. Thanks for joining the stand-up. I've been reviewing the design sprint progress…

01:16 – 03:45

Speaker 2 ▾

I'm currently focused on the backend tasks related to the API integration…

Rename Speaker 1

Enter new name
Rename Speaker

Synced playback

Never lose your place again

Read along while audio plays. Current section highlights automatically. Jump to any timestamped block, scrub with ±10s controls, and adjust playback speed.

  • Section timestamps on every block
  • Large play control with ±10s skip
  • Current section highlights as audio plays
  • Works with audio, video, and YouTube sources

Speakers & inline editing

Know who said what — and fix it fast

Automatic speaker labels keep multi-person meetings readable. Rename Speaker 1 and Speaker 2 to real names, edit text directly in-place, and bulk-update across all sections with one tap.

  • Automatic speaker detection with label assignment
  • Rename speakers in one tap with modal
  • Edit transcript text inline without leaving the view
  • Bulk-update a speaker name across all sections

00:00 – 01:15

Jesse Makanaki ▾Renamed

Good morning, everyone. Thanks for joining the stand-up. I've been reviewing the design sprint progress…

01:16 – 03:45

Speaker 2 ▾

I'm currently focused on the backend tasks related to the API integration…

Rename Speaker 1

Enter new name
Rename Speaker

Regeneration

Don't settle — regenerate

Not happy with the result? Free users get one free regeneration. Pro users can regenerate unlimited times for the best possible transcript. No need to re-upload — just tap Regenerate.

  • Free users: one regeneration per transcript
  • Pro users: unlimited regenerations
  • No re-upload needed — regenerates from stored audio

Select Transcription Type

Quick
Time ~2 minsAccuracy Standard
Basic transcriptionStandard timestamps
StandardPopular
Time ~5 minsAccuracy High
Enhanced accuracySpeaker detection
Premium
Time ~12 minsAccuracy Highest
Highest accuracySpeaker identification

Export

Ship transcripts in any format

Download PDF, TXT, SRT, VTT, or CSV. Toggle plain text, speakers, and timestamps. SRT and VTT formats are built for subtitling — drop them straight into your video editor or media player.

  • PDF, TXT, SRT, VTT, CSV — five formats
  • Free formats available on every plan
  • SRT / VTT for video subtitling workflows
  • Include speakers and timestamps as needed

Export Transcript

FreePDF Document
FreePlain Text (TXT)
FreeSubtitle (SRT)
FreeWebVTT (VTT)
ProSpreadsheet (CSV)
  • Only Text
  • Include Speakers
  • Include Timestamps
Export

Convert & compress

A media toolkit that never uploads your file

Change formats, shrink a recording, or extract a useful section without sending the file anywhere. Processing runs in your browser, and persistent jobs can be resumed after a reload.

  • Convert to MP3, M4A, WAV, OGG or WebM
  • Pull the audio out of any video file
  • Compression presets for speech, balance or quality
  • Three free conversions a day, unlimited on Pro
  • Extract a clip with precise start and end times
  • Queue multiple files and keep completed results locally
  • Very large files stream straight to a file you choose, not into memory
  • See the estimated output size first, then play the result before saving

Export Transcript

FreePDF Document
FreePlain Text (TXT)
FreeSubtitle (SRT)
FreeWebVTT (VTT)
ProSpreadsheet (CSV)
  • Only Text
  • Include Speakers
  • Include Timestamps
Export

Live notes

Notes while the meeting is still running

Start a session and watch editable text appear. Capture your own microphone, a meeting playing in another browser tab, or both at once — you choose per session. Recognition and storage stay on your device, and Live Notes does not create audio unless you explicitly enable local recording.

  • Capture your microphone, another browser tab, or both — chosen per session
  • On-device recognition, nothing uploaded
  • Runs for the length of a meeting, not a sentence
  • Edit, rename and keep sessions locally
  • Optional local recording with pause, resume and silence omission
  • Recover recording drafts after an interrupted session
  • Key points, action items and keywords, summarised by your browser on your device
  • Export notes to Markdown, DOCX, PDF or plain text
  • Send a local recording for a full cloud transcript in one step

Your transcription is being processed

This usually takes a few minutes. You can close this screen — we'll notify you when it's done.

Progress57%
  • Fetching media
  • Audio extraction
  • Language detection
  • Speech-to-text
  • Speaker identification
  • Timestamp alignment
  • Finalising

Backup & recovery

Keep notes local without losing them with the device

Notes that never leave your browser have one weakness: a cleared cache or a lost laptop takes them with it. Encrypt a backup in the browser and keep it as a file, or store it with us — either way, all we ever hold is ciphertext.

  • Encrypted in your browser with AES-GCM and a key derived from your passphrase
  • The passphrase never leaves your device, so we cannot decrypt the backup
  • Cloud backup is opt-in — notes stay local until you turn it on
  • Restore your notes and recordings in a new browser with the same passphrase

Export Transcript

FreePDF Document
FreePlain Text (TXT)
FreeSubtitle (SRT)
FreeWebVTT (VTT)
ProSpreadsheet (CSV)
  • Only Text
  • Include Speakers
  • Include Timestamps
Export

Private Studio · Pro

Finish sensitive work before it leaves your device

Pro includes a private editing bench for the last steps between a raw recording and something you are comfortable sending on: captions checked against the audio, clips cut to the exact range, and sensitive values found and masked before the file leaves your machine.

  • Fix captions against the audio itself, with a waveform strip marking every cue
  • Exact timecodes, plus split, merge, insert and retime — with undo, redo, and no export while timings are invalid
  • Readability warnings when a line runs too long or too fast to read comfortably
  • Pick a clip range on a single waveform slider and export just that audio, carrying the waveform as its cover art
  • Redaction finds names, emails, phone numbers, links, payment cards, IBANs, national identifiers, API keys, addresses, postcodes and dates
  • It also takes the value after a label such as “Policy ID”, “CVV” or “Account number”
  • Every detector is on by default, with presets for contact details or a full GDPR sweep
  • Accept or reject each match before it is applied, with the replacements highlighted
  • Mask with a label or a solid block, and add your own names or terms
  • Open a finished transcript straight into the caption editor or the redaction tool, and export as TXT, Markdown, DOCX, PDF, HTML or JSON

Export Transcript

FreePDF Document
FreePlain Text (TXT)
FreeSubtitle (SRT)
FreeWebVTT (VTT)
ProSpreadsheet (CSV)
  • Only Text
  • Include Speakers
  • Include Timestamps
Export

Workspace

Your transcripts, organised

A clean dashboard for everything you've transcribed — status chips for Transcribed, Processing, and Failed. Create new transcripts in one tap. Pro tools are ready when you need them.

  • Status at a glance: Transcribed, Processing, Failed
  • Create new transcripts in one tap
  • Web and mobile, same account and workflow
  • Pro banner with Unlock Pro CTA

Ready for more than occasional use?

Premium keeps ongoing work moving with unlimited transcription minutes, premium accuracy, speaker identification, unlimited conversion, Live Notes and the Private Studio.

Web appiOSAndroid coming soon
Compare paid plans

Turn the next recording into finished work

Start free, then choose Weekly for one project or Premium for unlimited minutes, premium accuracy, and unlimited private media tools.

Download on the
App Store
Try it in your
Browser

Start free · Upgrade when you need unlimited minutes and premium accuracy

Compare plans before you decide