How many speakers can the tool distinguish?

Up to 10 speakers are supported on the standard plan. Higher limits are available on Pro.

Does background noise affect accuracy?

Yes. Clean, low-noise recordings produce the best results. Noisy environments can reduce speaker separation accuracy.

Are my audio files kept private?

Audio files are stored only during processing and are permanently deleted immediately after the transcript is generated.

What is the maximum file size?

Free plan users can upload files up to 100 MB. Pro plan supports files up to 1 GB.

What is SRT format used for?

SRT is a subtitle format compatible with YouTube, Vimeo, and most video editing software, making it easy to add captions.

Can it handle recordings with overlapping speech?

The tool does its best to separate overlapping segments, but simultaneous speech from multiple speakers can reduce labeling accuracy.

Speaker diarization — Free Online

Drag audio/video

max 25 MB · Max 25MB

Auto-deleted in 7 days

256-bit SSL

Support

Your files are encrypted with SSL and automatically deleted from our servers 7 days after processing.

📖 How to Use

Enter content

Provide topic, text or prompt for AI.

Pick settings

Tone / length / format / language.

Generate

AI produces output in 10–30 sec.

Edit or download

Copy, download, or regenerate.

⚠️ This tool processes biometric data such as face or voice. Only use it with visual/audio content that is your own or for which you have obtained explicit consent (special category personal data under Turkish KVKK art. 6). Content is deleted from the server after processing.

🤖 Generated by AI. Information may be incomplete, inaccurate, or out of date — verify with a second source before making critical decisions. Responsibility for commercial use of the output lies with the user.

Speaker Diarization (who said what)

📖 How to Use