Start free
Audio files

Audio to text with timestamps and speaker labels

Transcribe audio to text by uploading a recording in the dashboard or through the API. Files up to 2 GB get a transcript with timestamps. Turn on speaker identification when you need to separate the voices.

Get your API keyRead the docs
  • mp3, wav, m4a, flac, ogg and opus
  • Uploads up to 2 GB
  • 1 credit per audio minute, rounded up

How it works

mp3 to text
Upload an mp3 recording and read or copy the completed transcript in the dashboard.
m4a to text
Upload an m4a file from your recordings. You can also transcribe wav, flac, ogg and opus files.
Optional speaker labels
Choose Identify speakers in the dashboard or send diarize=true through the API. The transcript labels voices as Speaker 1, Speaker 2 and so on.
Text with times
Every segment has start and end times. Download TXT for reading, JSON for your code, or SRT and VTT for captions.
Language per segment
AI speech-to-text reports each segment's language. Leave language on auto or pass a language hint.

Recordings

Transcribe a voice memo or interview

Upload your voice memo in a supported audio format. Read the transcript to find a passage, then use its timestamps to check the recording. The API accepts files up to 95 MB in one request.

cURL
curl -X POST "https://api.transcript1.com/v1/transcriptions?wait=60" \
  -H "Authorization: Bearer $TRANSCRIPT1_API_KEY" \
  -F [email protected] \
  -F language=auto

Larger files

Upload audio files up to 2 GB

The dashboard uses chunked uploads. Through the API, reserve an upload, send the chunks and complete it. This supports files up to 2 GB and lets an interrupted upload resume.

Reserve an upload
curl -X POST "https://api.transcript1.com/v1/transcriptions" \
  -H "Authorization: Bearer $TRANSCRIPT1_API_KEY" \
  -H "Idempotency-Key: interview-2026-10-13" \
  -H "Content-Type: application/json" \
  -d '{"upload":{"filename":"interview.m4a","size":48210334,"mime_type":"audio/mp4"}}'

Start with 60 free minutes

60 free minutes after you verify your email. No card required.

Get your API key

Frequently asked questions

Something missing? Ask support

Which audio files can I transcribe to text?

mp3, wav, m4a, flac, ogg and opus. Upload the file through the dashboard or API.

How large can an audio upload be?

Chunked uploads accept files up to 2 GB. A one-request API upload accepts up to 95 MB.

Can the transcript identify speakers by name?

Speaker identification gives labels such as Speaker 1 and Speaker 2. It does not identify real names. Set diarize=true to request these labels.

Can I try audio transcription for free?

You get 60 free minutes once after email verification, with no card required. Transcription costs 1 credit per audio minute, rounded up. Failed and canceled transcriptions are not charged.

Related