Transcribe Audio to Text

Transcribe audio to text online with timestamps, speaker labels, and export to TXT, SRT, or VTT — upload a recording and get an editable transcript in your browser.

Click to upload or drop an audio file

Supports MP3, WAV, AAC, M4A, FLAC, OGG

Up to 2 GB per file

Source video up to 60 minutes

Very long videos may fail when extracted ASR audio exceeds 100MB — trim first if needed

Upload a video first to adjust settings and preview the result

How to transcribe audio to text

Upload a recording, select the language, and start transcription. The result appears as timed lines you can scroll, edit, and export — useful when you need searchable text rather than listening through the whole file again.

  1. 01

    Upload audio

    Add MP3, WAV, M4A, FLAC, or other common audio formats from your device.

  2. 02

    Choose language

    Select the spoken language. Timestamps and speaker labels are generated as the transcript is built.

  3. 03

    Export text or subtitles

    Download TXT for notes, or SRT/VTT for caption workflows — edit lines in the browser before export.

Audio & voice

Transcription with timestamps

Each line is tied to a moment in the audio, so you can jump back to verify a quote or trim a clip to match the words. Timestamps carry through to SRT and VTT exports for subtitle workflows.

Add video or subtitles
Audio & voice

Speaker separation

When multiple people talk, speaker labels help you tell who said what — handy for interviews, panel discussions, and meeting notes. You can still edit labels in the transcript before export.

Add video or subtitles
Audio & voice

Export TXT, SRT, and VTT

TXT works for articles and search. SRT and VTT feed caption generators and video editors. Pick the format that matches your next step instead of retyping from scratch.

  • TXT — plain text for notes and scripts.
  • SRT — standard subtitle format for most players.
  • VTT — web-friendly captions for HTML video.
Add video or subtitles
Audio & voice

Supported languages and formats

Multiple languages are supported for recognition. Common audio containers and codecs work on upload; file size and length limits are shown before processing starts.

Add video or subtitles

Built for these real workflows

Podcast production
01

Podcast production

Voiceover and localization
02

Voiceover and localization

Track cleanup and mixing
03

Track cleanup and mixing

Frequently asked questions

Is transcription free?

You can try within the free quota. Longer files or batch jobs may use credits — see pricing for current limits.

Which languages are supported?

A wide range of spoken languages is available at upload. Pick the language that matches the recording for best results.

Can I export as subtitles?

Yes. Export SRT or VTT with timestamps, then use them in a caption tool or video editor.

Start using Audio to Text

Provide the input and essential settings above. Your result stays in the current tool workflow.

Back to tool