Speech to Text

Convert an audio recording into an editable transcript. Review speech-to-text results and export TXT, SRT or VTT subtitles in DIY AI Studio.

Speech to text converts spoken audio into a written draft. It can help with interview notes, short recordings and subtitle preparation. Automated transcripts can contain errors, especially with overlapping speakers, background noise or technical terms.

Skip to workspace

Turn your recording into editable text.

Add an MP3 or WAV recording, then review the transcription cost.

Fish Audio

Speech to Text

Turn a short recording into an editable transcript with segment timestamps.

The server checks the actual audio duration before calling Fish. Speaker identification, translation and word-level timestamps are not included.

Sign in to transcribe audio.

Your recording. Ready to read. — concept artwork
Concept artworkYour recording. Ready to read.

Example artwork. Your result will appear here after generation.

How to use Speech to Text

Transcribe audio and prepare subtitles

Speech to text converts spoken audio into a written draft. It can help with interview notes, short recordings and subtitle preparation. Automated transcripts can contain errors, especially with overlapping speakers, background noise or technical terms.

How to use this tool

Upload a supported MP3 or PCM WAV recording, select the language hint and start transcription. Review the text against the audio before downloading your transcript or timed subtitles.

Tips for a better result

  • Use a clear recording with as little background noise as possible. One speaker at a time is easier to review than overlapping conversation.
  • Select the language hint that fits the recording and check names, figures and technical vocabulary against the audio.
  • Review text and timings separately. Download TXT for your edited wording, or SRT and VTT when you need the original timed subtitle segments.

Frequently asked questions

Are subtitle exports the same as my edited transcript?

TXT uses the text you edit in the browser. SRT and VTT use the original timed segments, so check their wording and timings separately.

Membership, credits and privacy

You can explore the tool before signing in. Generating requires an active Studio membership and enough credits. Eligible new members can start with 50 credits for $0.99 for seven days, then $9.99/month with 100 credits unless cancelled. Review the current terms when joining; the credit price for your recording or edit is shown before it starts.

Results are private to your account. Unsaved results expire after seven days. Use Save to keep results in your Saved section and protect them from automatic cleanup. Voice references remain available for 30 days, or longer while their recording is saved. You can delete results and voices at any time.

WORKING IN THE BACKGROUND

Your generations

Keep creating. Your work continues as you move around Studio.