Speech to Text — Turn Recordings and Video into Transcripts

Upload a file and AI returns a timestamped transcript you can copy straight out

Supports WAV, MP3, MP4, M4A and other common audio and video formats, up to 100 MB per file. Detect the language automatically, separate different speakers, and switch the output format to suit meetings, interviews, lectures and podcasts.

How the Speech to Text Tool Works

1. Sign up and upload your file

Create an account, then upload an audio or video file. WAV, MP3, OGG, OPUS, FLAC, AAC, MP4, M4A and MKV are supported, up to 100 MB per file.

2. Set the language and speaker separation

Choose the language of the recording or let automatic detection handle it. If several people are talking, turn on speaker separation to keep each voice apart.

3. Get a transcript with timestamps

The AI converts the audio or video into text and marks timestamps, so you can jump back to the matching moment in the original file.

4. Review the details and copy the result

When it finishes you can see the file length, word count, detected language and number of speakers. Switch the output format, then copy the text and keep working.

Everything a Transcript Needs, in One Place

Audio and video both work

Common audio and video formats are supported, so meeting recordings, interviews, lectures and podcasts can all be turned into transcripts.

Automatic language detection

When you are not sure which language to pick, let the tool detect it and skip the manual setup.

Check quickly with timestamps

Transcripts are marked with timestamps, so you can find the matching part of the original recording without replaying it from the start.

Tell speakers apart

Turn on speaker separation and multi-person conversations are laid out per speaker — useful for meetings, interviews and any dialogue.

See the transcription details

File length, word count, detected language and speaker count are all shown, so you can size up the result at a glance.

Switch format and copy

Pick the output format that suits what comes next, then copy the text straight into notes, meeting minutes, a subtitle draft or any other document.

Speech to Text FAQ

Do I need an account to use the speech to text tool?

Yes. Sign up and log in to use the tool. New accounts come with free credits and no card is required.

Is a subscription required?

No. The platform runs on credits and deducts them based on usage — there is no forced subscription plan.

Which file formats are supported, and is there a size limit?

WAV, MP3, OGG, OPUS, FLAC, AAC, MP4, M4A and MKV are supported. Each uploaded file can be up to 100 MB.

Can it detect the language of the file automatically?

Yes. You can set the language yourself, or use automatic detection and let the tool work out what is in the file.

Can it separate speakers in a multi-person recording?

Yes. Turn on speaker separation after uploading and the transcript will distinguish between speakers and show how many there were.

Can I paste a YouTube link to transcribe it?

No. This tool does not pull content from a URL — upload an audio or video file that you have the right to use.