TalkScribe
Log inTry TalkScribe free
6 languages, auto-detected

Turn conversations into transcripts, minutes and subtitles.

Accurate transcription with speaker recognition, AI meeting notes you can verify, and subtitles in five more languages.

No credit card required. Google or email sign-up.

Speaker-labelledWord-level timestampsDOCXPDFSRTVTT
New transcriptFree plan · 3 files today
Drop audio or video here
MP3 · WAV · M4A · MP4 · MKV · OGG · FLAC · WMA
Recognise known voicesonce you save voice profiles
45 min ≈ 4 min

Three transcripts a day on the free plan, up to 30 minutes each.

How it works

Three steps from recording to finished work

1
Upload anything recorded

Audio or video, one file or a queue. Language, number of speakers and glossaries are detected or set per file.

Progress with stage and ETA
2
Review in the editor

Play with the waveform, fix a word, rename a speaker everywhere, accept glossary suggestions.

Ctrl+Space play · Ctrl+F search
3
Turn it into finished work

Export DOCX or PDF, generate minutes, action items, subtitles, chapters or a call report.

Every item timestamped
Accuracy & speakers

“Speaker 2” becomes a name

Word-level timing keeps the highlighted word on the audio. Speakers are separated automatically, and people TalkScribe has met before are recognised by voice — it asks instead of guessing when it isn’t sure.

The highlighted word follows playback, so you can read and listen at once.
Rename a speaker once and it changes across the whole transcript.
Glossaries keep names and jargon spelled your way — “next jest” becomes “Next.js”.
Explore the editor →
product-review.mp49 utterances · 142 wordsEnglish (98%)
00:00Anna Whitfield
Good morning, Ms Weber. Thanks for making time today.
00:10Speaker 2
Good morning. I do have a few questions about the schedule.
00:23Speaker 2
The first phase is meant to close in October.
00:33Anna Whitfield
I understand the concern. All migrations will be tested by the end of next week.
Speakers
Anna Whitfield
🎙 Recognised 91%
31 s · 57% · 5 utterances
Speaker 2
Is this James Carter (74%)?
YesNo
23 s · 43% · 4 utterances
AI that shows its work

Every item links to the moment it was said

Minutes, action items, summaries, chapters and your own templates. Hover an action item to see the sentence it came from. If the transcript doesn’t support an item, TalkScribe removes it.

Meeting minutesUp to dateEnglish output
🛡 Removed 2 items not supported by the recording.
Decisions
▶ 00:33All migrations will be tested by the end of next week.
▶ 00:45Two external consultants join for the busiest weeks.
Action items
WhoWhatDueMoment
Anna WhitfieldSend the migration summary to all participantsToday▶ 01:01
James CarterConfirm the Munich data hand-over dateFri, 18 Sep▶ 00:23
unassignedBook the follow-up meeting in two weeks—▶ 00:52
DOCXPDFMarkdownCopy
Source transcript
00:00Anna Whitfield
Good morning, Ms Weber. Thanks for making time for the review today.
00:23Speaker 2
The first phase is meant to close in October, but I am not sure the Munich team will have the data ready in time.
00:52Speaker 2
Then I suggest we meet again in two weeks and go through the progress.
01:01Anna Whitfield
Agreed. I will put together a short summary and send it to everyone today.
Hover an action item on the left — the sentence it was taken from is highlighted here.
Meeting minutes

Participants, decisions, action items and a short summary.

Action items

Editable table: who, what, by when, and the moment it was agreed.

Chapters

Time-stamped chapter list, ready to copy into a YouTube description.

Custom templates

Your own instruction and sections, reusable across recordings.

Call analytics

Review sales and support calls, not just read them

Talk share, pace, longest monologue, interruptions and questions — plus a scorecard you can edit to match your own process. Every criterion carries the justification and the moment it was met.

Sales & support use case →
72%BANT score
Rep 58%Customer 42%
Pace 148 wpmLongest monologue 2:14Interruptions 3Questions 11
BudgetMetCustomer named a range for the 2027 budget.▶ 04:12
AuthorityPartialDecision maker mentioned but not confirmed.▶ 07:48
NeedMetTwo concrete problems with the current workflow.▶ 11:02
TimelineNot metNo date discussed for the decision.▶ —
Objections & responsesNext steps with ownersSentiment start · middle · end
Subtitles · Chinese (Simplified)14/16 · 1 needs review · 2 to translate42 chars/line · 17 chars/s
TimeSpeakerOriginalTranslationStatus
▶ 00:12AnnaLet's start with the migration status.我们先从迁移状态开始。OK
▶ 00:19JamesThe first phase closes in October.第一阶段将在十月完成。Edited
▶ 00:27JamesWe need to check invoicing in KSeF.我们需要检查 KSeF 中的发票。Needs review
▶ 00:41AnnaI'll send the summary today.我今天就发送摘要。Outdated
SRTWebVTT18 cues · 4 too fast
Subtitles & translation

Reviewed before they leave the app

SRT and WebVTT with professional readability rules — up to 42 characters per line and 17 characters per second. Translate into up to four more languages and check every sentence before export.

Edit the transcript afterwards and only the changed sentences are re-translated.

EnglishPolishGermanFrenchSpanishChinese (Simplified)
Input

MP3 · WAV · M4A · MP4 · MKV · OGG · FLAC · WMA

Output

DOCX · PDF · Markdown · SRT · WebVTT · copy to clipboard

Languages

English · Polish · German · French · Spanish · Chinese (Mandarin), auto-detected

Privacy first

Voice data treated as what it is

Voice profiles are biometric data. Creating one requires a recorded legal basis or consent, and you can switch recognition off at any time.

Security & privacy →
Encrypted voice prints

Voice prints are encrypted and never included in transcripts, exports, subtitles or AI documents — only names are.

Consent on the record

Creating a voice profile requires a legal basis or consent, stored with the profile.

Delete means delete

Deleting a voice profile deletes all of its voice samples.

Your switch

Voice recognition can be switched off at any time, per account or per file.

Pricing

Start free, upgrade when you need more

save 43% yearly
Free
$0forever

Enough to judge the quality on your own recordings.

Start for free
✓3 transcripts per day, up to 30 minutes each
✓Full editor with waveform and speaker labels
✓DOCX and PDF export
✓6 recording languages, auto-detected
ProMost popular
$14/ month

Unlimited transcription and the full editor.

Start free trial
✓Unlimited transcription, fair use
✓Files up to 10 hours, 5 processing at once
✓Voice profiles and custom glossaries
✓Subtitles in the original language
AI
$25/ month

Adds minutes, call analytics and translation.

Start free trial
✓Everything in Pro, plus AI documents
✓Minutes, action items, chapters, templates
✓Call analytics and scorecards
✓Translation into 4 more languages

Yearly billing is one charge: $96 for Pro, $240 for AI. Unlimited means 10 hours per file and five files at once. Full plan comparison →

What people say

Placeholder content

The minutes arrive with owners and deadlines already filled in. I check the timestamps and send them.

Placeholder name
Project Manager

I review calls by scorecard instead of listening to an hour of audio to find two minutes.

Placeholder name
Sales Director

Speaker names stay right across a whole interview series, so quotes are safe to publish.

Placeholder name
Journalist

Chapters and subtitles in two languages take minutes, not an evening.

Placeholder name
Podcaster

Our glossary means product names are spelled correctly in every transcript.

Placeholder name
Support Lead

Consent is recorded with every voice profile, which is what our legal team asked for.

Placeholder name
HR Manager

Questions

Transcription with speaker recognition, AI documents you can verify, subtitles with translation, and analytics for sales and support calls — in one place.

Ready to stop taking notes?

Upload a recording and see the transcript, speakers and minutes for yourself.

Start transcribing for freeTalk to sales

No credit card required. Cancel any time.