What file types and sizes are supported?

Audio and video up to 450 min: MP3, WAV, M4A, AAC, OGG, FLAC, MP4, MOV, MKV and WebM. The audio track is extracted automatically from video files.

Which formats can I download?

SRT, VTT and plain-text TXT, one set per language. You can also re-download your original media at any time.

How does pricing work?

One credit equals one minute of media, per language, rounded up to the whole minute. A 10-minute file transcribed and translated into two languages costs 10 × 3 = 30 credits. The wizard shows a live cost preview and your post-job balance before you start.

What happens to my files and data?

Uploaded media and generated transcripts are automatically cleaned after a retention window, so your content does not sit on our servers indefinitely.

Can I get a refund on credits?

Credits are pre-purchased through Stripe and shown transparently before every job. Reach out to support for any billing issue and we will make it right.

AI speech to text, in minutes

AI speech to text — turn any audio or video into accurate subtitles.

Upload media and get clean, well-timed captions from AI speech to text (voice to text) plus multilingual translations — ready to download as SRT, VTT and TXT. Pay only for the minutes you use.

Start free See how it works

450 min max·~1 credit / min·No subscription

So today we're walking through the entire workflow, start to finish.

live preview

02:41 / 08:32

CCEnglishEspañolFrançais日本語

How it works

Three steps from raw file to finished captions.

Upload

Drag in any audio or video — MP3, WAV, M4A, MP4, MOV, MKV, WebM and more, up to 450 min.

Choose languages

Pick the source language or auto-detect it, add target languages to translate into, and toggle automatic punctuation.

Confirm & download

See a transparent cost preview, start the job, watch it process live, then download SRT, VTT and TXT per language.

Features

Everything you need to caption and localize.

AI speech to text

Accurate speech to text (voice to text) with automatic punctuation and capitalization, segmented into clean, well-timed cues — not one giant block.

Multi-language translation

Transcribe the source, then translate captions into multiple target languages — all in the same job.

Ready-to-use formats

Download standard SRT, VTT and TXT per language — plus re-download your original media any time.

Preview before export

Play your media with captions rendered live and switch caption tracks before you download a thing.

Pay only for what you use

Buy credits, spend ~1 per minute per language. No subscription lock-in, and a live cost preview every job.

Real-time progress

Watch upload → extracting → recognizing → translating → completed, live, without ever refreshing the page.

Inside the app

A Studio for every job, and a wizard that shows the cost up front.

Studiobalance 470 cr

product-launch-keynote.mp4

EN · ES · FR · 12:48

Completed39 cr

weekly-podcast-ep-42.mp3

EN · 48:12

Recognizing49 cr

onboarding-tutorial.mov

EN · DE · 06:30

Completed14 cr

webinar-q2-recap.mkv

EN · JA · KO · 58:04

Translating—

✓Upload

2Languages

3Confirm

Source language

English (US)Auto-detect

Translate into

SpanishFrench+ add

Estimated cost · 12:48 × 3 langs

39 credits

Balance after

431

Pricing

Pay as you go. One credit ≈ one minute, per language.

No subscription, no lock-in. Buy a pack of credits and spend them only when you process media.

Estimate your job

Minutes of media12 min

Languages (1 source + translations)3

You'll spend

36

credits

12 min × 3 langs · ≈ $1.20

Starter

$4.99

100 credits · $0.05 / min

Buy pack

People who ship with TranSpeaker.

“I was skeptical of AI transcription after bad experiences elsewhere, but the punctuation and accent handling here is genuinely production-grade.”

Daniel Ibáñez

Freelance Journalist

“We localize training videos into three languages every month. Credit-based pricing is so much easier to budget than a subscription.”

Rodrigo Fuentes

L&D Manager, Cobalt Learning

“Switching subtitle languages for our YouTube channel used to take a full day. Now it is one upload and a few clicks.”

Tomás Reyes

Content Creator

FAQ

Questions, answered.

TranSpeaker uses production speech-to-text with automatic punctuation and capitalization. Output is segmented into clean, well-timed cues rather than one long block — and you can preview every caption in the player before exporting.

Subtitles and translations, in minutes.

Upload your first file and see accurate captions render live. 10 free credits to start.

Start free