Gitruck Toolbox

Audio to Text

Turn speech in recordings and videos into a transcript, with TXT and SRT / VTT subtitle exports

Runs on cloud
Files are processed on Gitruck Cloud. You see the price first, and failed jobs are free.
Checking the price…Pricing details
Need batch or automated processing? Use the gtrk CLI
$ gtrk transcript ./interview.mp4

Pricing

Checking the price…

How to use

  1. 1

    Sign in, then choose or drop audio or video files. You can add several at once.

  2. 2

    Pick the spoken language on the left, then click Submit.

  3. 3

    Download the full text (TXT), or SRT / VTT subtitles ready for your editor.

FAQ

Which languages are supported?

More than a hundred, including Mandarin, Cantonese, English, Japanese, Korean, Spanish, French and German. Pick the spoken language for accurate results; if two languages are mixed, pick the one used most.

Which formats can I export?

Full text (TXT, one sentence per line), SRT and VTT subtitles with timings for CapCut, Premiere, YouTube and others, and the raw JSON with word timings.

Can I transcribe a video?

Yes. Your browser takes out the audio first and uploads only that, so large videos don't have to be uploaded in full.

Want subtitles on a video, translated or burned in?

Use AI Auto Subtitles: lines are broken to fit the picture, and you can translate into bilingual subtitles, pick a style and burn them in. Audio to Text is better for transcripts or less common languages.

Can it tell who is speaking?

For a transcript split by speaker, use Meeting & Interview Transcription: every line is labeled with who said it, and you can rename speakers and export to Word.

Does it cost credits?

It's billed by length: your first 200 runs of this tool cost 1 credit per minute, then 2 credits per minute, prorated and rounded up to a whole credit. Live prices and full rules are in Pricing on this page. You need to sign in; failed runs are refunded.

How long can a file be?

Up to 2 hours per file.

Meeting & Interview Transcription

Transcribe meetings, interviews and podcasts with speaker labels. Rename speakers, replay any line, and export to Word, TXT or subtitles

Long Image to Square

Cut tall or wide images into strips and lay them side by side as an easy-to-read square

Image Aspect Ratio Converter

Convert images to landscape, portrait or any ratio, with a blurred background that blends in

Image Background Remover

Cut out people or objects and make the background transparent, keeping soft edges like hair