Transcribe audio and video into transcripts you can actually work with.
Scribetide is an AI transcription service for meetings, interviews, lectures and sermons. Upload audio or video, paste a link, or record in the browser, and get an accurate transcript with speaker names, an editor built for fixing it fast, AI notes, translation and 7 export formats.
Free plan: 3 files a day, up to 30 minutes each. No card needed.
A fictional team meeting written for this demo: the first 8 passages of 6:12. Press play or click any word to move the playhead; no audio plays.
A workspace built for fixing transcripts
Automatic transcription gets you most of the way. The rest is names, numbers and the odd misheard word, so the editor is built around fixing those quickly while you listen.
Speakers
Every passage carries a speaker label. Rename A, B and C once and the whole transcript updates.
Editing
Click a passage and fix it in place. Changes save as you type; merge passages with one action.
Find and replace
Correct a misheard name across the whole transcript at once, case-sensitive or not.
Review
Play along at 0.5x to 2x. The current passage and word stay highlighted, so you always know where you are.
Private by default
Recordings are sensitive. Storage is private, the audio can delete itself on a timer, and the only services that ever see your data are the ones doing the transcription and the notes.
Private storage
Recordings live in a private bucket only your account and the server can read. Media is served through short-lived signed links.
Retention timers
Delete the original audio automatically: right after transcription, after 24 hours, 7 days, 30 days, or never.
Delete audio now
One click removes the media while the transcript stays exactly as it is.
No training on your data
Nothing you upload trains a model, by us or by the services we use to transcribe and summarize.
Outputs you can hand to someone
Turn an hour of talking into the thing people actually read: a summary, a list of decisions, subtitles, or a clean document.
AI notes
Quick summary, detailed summary, action items, meeting minutes, outline, sermon notes, or your own prompt.
7 export formats
TXT, Markdown, DOCX, PDF, SRT, VTT and JSON, with or without speakers and timestamps.
Copy in one step
Plain text, with speakers, or with timestamps, straight to the clipboard.
Smart titles
A short descriptive title is suggested after transcription. The original filename is always kept.
How it works
Upload, paste a link, or record
MP3, WAV, M4A, AAC, FLAC, OGG, OPUS, AIFF, WMA, AMR, MP4, MOV, WEBM, M4V, MKV, AVI, WMV, 3GP or MTS, up to 5 GB — or paste a media link, or record straight into the browser. Uploads resume if the connection drops.
We transcribe it
Speaker labels and automatic language detection across 25 languages. Most hour-long recordings finish in a few minutes.
Edit, summarize, export
Fix names, generate notes, and export in the format the next person needs.
Simple pricing
Start free. Upgrade when you need longer files or more of them.
Free
For the occasional recording.
$0
No card needed
- 3 files a day
- Up to 30 minutes per file
- Files up to 500 MB
- Speaker labels, editing, find and replace
- AI notes and translation (20 a month)
- Seven export formats
- Standard queue
Unlimited
For people who transcribe every week.
$12/month
or $96 a year ($8 a month)
- Unlimited files
- Up to 10 hours per file
- Files up to 5 GB
- 100 hours of transcription a month (fair use)
- Speaker labels, editing, find and replace
- AI notes and translation (300 a month, fair use)
- Seven export formats
- Priority queue
Questions
How accurate are the transcripts?
Scribetide transcripts are usually ready to share after one read-through when the audio is clear: one person speaking at a time, a decent microphone, little background noise. Crosstalk, noise and unusual names lower accuracy. Transcription runs on AssemblyAI's Universal speech model with speaker labels; review mode underlines the words the model was unsure of so you check the doubtful spots first, key terms you add before transcribing help with names and jargon, and the editor is built for fixing the rest fast.
Which languages are supported?
Scribetide transcribes 25 languages, including English, Spanish, French, German, Portuguese, Japanese, Chinese, Korean, Arabic and Hindi. Leave the language on automatic detection or set it for each upload.
Does it tell speakers apart?
Yes. Scribetide labels every passage with a speaker, on every plan. Rename a speaker once and the name updates everywhere, including exports. If you know how many people are talking, set the number before transcribing to improve the split.
Can I transcribe a YouTube video?
YouTube links do not work on Scribetide right now: YouTube blocks downloads from cloud servers, and Scribetide tells you immediately instead of failing silently. Download the audio yourself and upload the file, or paste a direct media link into the Link tab, where every supported format works normally.
Can I record straight into the browser?
Yes. Scribetide has a Record tab that captures from your microphone and sends the recording for transcription the moment you stop, with nothing to install. It is meant for the interview, lecture or meeting in front of you — it does not join a Zoom or Teams call as a bot, so for those, upload or link the recording the platform saves.
Can I translate a transcript or get bilingual subtitles?
Yes. Scribetide translates a finished transcript into another language and exports it as SRT or VTT — either the translation on its own, or bilingual subtitles with the original line above the translated one. The timings stay tied to the original audio, so the subtitles still line up with the video.
How do I get names and jargon spelled right?
Add names and jargon to Scribetide's personal glossary and the speech model spells them your way from then on. Terms in your glossary are sent with every transcription, and you can also add key terms for a single upload. Anything that still slips through is one find-and-replace away in the editor.
How do I find the words the model probably got wrong?
Turn on Scribetide's review mode. It underlines every word the speech model scored below 60% confidence and steps you through them one at a time while the audio plays, so you check the doubtful spots instead of re-reading the whole transcript. The threshold is a slider from 30% to 90%.
How much does Unlimited cost?
Scribetide Unlimited is $12 a month, or $96 a year — $8 a month, billed once, which is 33% less than paying monthly. Prices are in US dollars. Unlimited lifts the daily file cap, raises the per-file limit to 10 hours, and includes 100 hours of transcription a month as fair use; Scribetide's free plan stays free at 3 files a day, up to 30 minutes each, with no card.
What are the file limits?
Scribetide Free takes 3 files a day, up to 30 minutes and 500 MB per file. When the browser cannot read a file's duration — and on every link import on Free — the Free size limit is 60 MB instead. Unlimited takes files up to 10 hours and 5 GB, with 100 hours a month as fair use. Supported formats: MP3, WAV, M4A, AAC, FLAC, OGG, OPUS, AIFF, WMA, AMR, MP4, MOV, WEBM, M4V, MKV, AVI, WMV, 3GP and MTS.
Who can see my recordings and transcripts?
Only you. Scribetide keeps recordings in a private bucket tied to your account and serves them through short-lived signed links. To transcribe, AssemblyAI receives a temporary link to the audio; Anthropic or OpenAI receives the transcript text and your instruction when you run an AI tool or translation, and to suggest a title when a transcript finishes (you can turn smart titles off in Settings). Neither we nor those services train models on your data, nobody else receives it, and you decide how long the audio is kept.
Can I cancel anytime?
Yes. Cancel Scribetide Unlimited from Settings and it stays active until the end of the period you already paid for. There are no refunds for partial months or years. Your account moves back to the free plan and your transcripts stay yours.