Every word of your recording, written down
This speech to text tool transcribes an audio file into text with per-segment timestamps, and tells you which language it heard. Copy it, read it in full, or download it as a .txt file or .srt subtitles for your video editor.
How it works
- 1
Add your audio
Upload a file, pick one from your library, or paste a public URL. One audio file per run.
- 2
Choose the task
Keep the source language or translate to English, and set the language or leave it on auto-detect.
- 3
Transcribe
The transcript appears on its card when it is done, ready to copy or download.
What you can make
Podcasters
Turn an episode into show notes, a blog post or quote cards without typing it out by ear.
Journalists and researchers
Get an interview down as text with timestamps, so you can jump back to the exact quote.
Video editors
Export the .srt and drop it straight into your editor as a subtitle track.
Indonesian creators with a global audience
Translate an Indonesian voice note or talk straight into English text for captions and posts.
This speech to text tool transcribes an audio file into text with per-segment timestamps, and tells you which language it heard.
Transcribe your first recordingSpecs & limits
| Input | One audio file: mp3, wav, m4a, ogg or aac |
|---|---|
| Tasks | Transcribe in the source language, or translate to English |
| Languages | Auto-detect, or pick from 17 including Indonesian, English, Japanese and Arabic |
| Output | Transcript with per-segment timestamps and the detected language |
| Downloads | .txt and .srt, or copy to clipboard |
| Billing | Per minute of audio, rounded up, 1-minute minimum |
Tips for better results
- Got a video? Extract the audio first. The source picker only accepts audio files, so a video will not show up there.
- Clean audio beats a long file. Background music under the voice costs accuracy, so trim intros and outros with music before you run it.
- Set the language yourself if the speaker mixes Indonesian and English. Auto-detect settles on one, which can throw off the other half.
- Download what you want to keep. Transcripts live on their card and are not saved to your media library.
- Give it a title if you transcribe a lot. Leave it blank and one is made for you, but your own name is easier to find later.
Frequently asked questions
Can it translate into Indonesian or other languages?
No, translation goes to English only. Any of the supported languages can go in, and the translated text comes out in English at the same rate as a plain transcript.
Can I get subtitles out of it?
Yes. Download the .srt and import it into your video editor. If a transcript comes back without timestamps, the .srt button is turned off, but the .txt still works.
Where is the transcript saved?
On the transcript card in the tool, where you can view, copy or download it. It is not added to your media library, so download anything you want a copy of.
Is it free?
No. Each run spends AI credits from your Wujud account, billed per minute of audio with a 1-minute minimum, based on the real duration once it is transcribed. Credits are bought as a pack and new accounts start with none. The tool needs a paid plan.
Related tools
An animated waveform and captions over your podcast clip, so it still lands with the sound off. Square, vertical or landscape. Make your first one now.
Dub a video into another language and lip-sync it back — transcribed, translated and voiced in one pass. 11 languages including Bahasa Indonesia. Try it now.
Paste up to 5,000 characters and get a natural voiceover back. 30 voices, multi-speaker dialogue, 17 languages, MP3, WAV or OGG. Write your first script.