Artgen
Artgen
Start creatingCreate

Audio workspace

Speech to text

Transcribe MP3 or WAV audio into text in Artgen. Review the transcript, follow timed segments, and export text or available subtitles.

Open in Create

Upload an MP3 or WAV file, or select an audio asset from your library. The workspace checks the selected model’s file and duration limits.

Open in Create

What you can make

Source audio

Upload an MP3 or WAV file, or select an audio asset from your library. The workspace checks the selected model’s file and duration limits.

Timestamps

Choose a transcription model. Language, timestamp precision, and speaker labels are offered only when the model supports them.

Transcript

Review the transcript beside the original audio. Copy the full text or export TXT and JSON; SRT and VTT require available timestamps.

How it works

  1. Upload audio

    Upload an MP3 or WAV file, or select an audio asset from your library. The workspace checks the selected model’s file and duration limits.

  2. Model

    Choose a transcription model. Language, timestamp precision, and speaker labels are offered only when the model supports them.

  3. Transcribe audio

    Review the transcript beside the original audio. Copy the full text or export TXT and JSON; SRT and VTT require available timestamps.

Review the quote before starting. Credits are reserved only when you submit.

Questions

Can I transcribe a video directly?

This version accepts MP3 and WAV audio. Export the audio track from your video first, then upload that file.

Why are subtitle downloads sometimes unavailable?

SRT and VTT need timed speech segments or words. When the selected model returns plain text only, TXT and JSON remain available.

Related tools