SpeedTranscriptStart from the file you have
Open common formats such as MP3, WAV, and M4A. An iPhone voice memo can go straight from Files into the tool.
Accurate AI transcription · speaker labels
Voice Recording to Transcript
Upload a voice memo, meeting recording or interview and get an accurate transcript with timestamps and speaker labels, ready to edit and export. 99 languages, no subscription.
Upload a voice recording
Drag and drop audio here, or choose a file.
MP3, WAV, M4A and more · Up to 500 MB · Speaker labels
- Flagship speech model
- Speaker labels included
- 99 languages detected
- 6 export options
- 2 free credits on signup
The essentials
Why SpeedTranscript for Voice Recording Transcription
Find the right moment
Click a timestamp to seek to that segment. Check the quote or phrase without replaying the entire recording.
Work across languages
The speech model recognizes 99 languages and detects the spoken language automatically.
Review before you share
Fix names, technical terms, and punctuation in each segment. Add speaker names wherever the reader needs them.
Know exactly what is uploaded
Nothing leaves your browser until you press Upload & transcribe, and the notice above the button spells out who processes the audio and for how long.
Take the text with you
Copy the transcript or export TXT, DOCX, SRT, VTT, or JSON. Save a PDF from your browser’s print dialog.
From audio to text
How to Turn a Voice Recording into a Transcript
Choose a recording
Drop in a saved voice memo, meeting, or interview. Files up to 500 MB are accepted, and choosing one needs no account.
Transcribe
Sign in, choose a file, and select Upload & transcribe. New accounts get 2 free credits; 1 credit covers 30 minutes of audio.
Check the wording
Use the audio player and timestamps to check names, numbers, and any unclear passages.
Export your transcript
Copy the text, save a document, or download timed captions for a video.
Perfect for Every Recording
Meetings
Check who agreed to an action and when it came up.
Interviews and podcasts
Find a quotable line and jump to the original audio.
Lectures
Search a recorded class for a term you missed.
Content creation
Start a subtitle track or pull excerpts for a draft.
Frequently Asked Questions
How can I turn a voice recording into a transcript?
Sign in, choose a saved audio file, and select Upload & transcribe. The transcript arrives with timestamps and speaker labels; play the recording back and correct any words before you export.
Can I transcribe a recording for free?
Yes, you can try it without paying. New accounts get 2 free credits once, which covers about one hour of audio in total, and no card is required. After that, 1 credit covers 30 minutes of audio and packs start at $9.99 for 20 credits. Choosing a file is free; starting a transcription is what spends a credit.
Can I transcribe an iPhone voice memo?
Yes. In Voice Memos, share the recording and save it to Files. Choose that M4A file in the transcription tool.
How do I convert a WhatsApp voice note to text?
Save the voice note to your device and select it here. If your browser cannot read the exported Opus file, convert it to WAV or MP3 first.
What audio formats can I upload?
Try MP3, WAV, M4A, AAC, FLAC, OGG, Opus, or WebM. Codec support depends on your browser. If a recording fails to open, try MP3 or WAV.
Can I transcribe a long audio recording?
Yes. Files up to 500 MB are accepted, and long recordings are charged in 30-minute blocks: a 2-hour interview uses 4 credits. Jobs run asynchronously, so you can close the tab and reload the page to pick the transcript back up.
How accurate is AI transcription?
We route every file to the most accurate model available for its language, keep punctuation and number formatting on, and add speaker labels. On clean recordings of a single speaker accuracy is high; background noise, strong accents, crosstalk, and unusual proper nouns are where errors appear. Replay uncertain segments and check names, numbers, and quotes before sharing — every segment stays editable.
Which languages can I transcribe?
AssemblyAI Universal-2 supports 99 languages and detects the spoken language automatically. Accuracy varies by language and recording quality.
Can it tell who is speaking?
Yes. Every transcript includes inferred speaker labels (Speaker A, Speaker B, and so on) that you can rename before exporting. Check the labels against the recording: short replies, overlapping speech and similar voices can be misattributed.
Does my audio get uploaded?
Yes, transcription runs in the cloud. Your recording is sent to AssemblyAI in the United States, which returns the transcript; we delete the vendor-side transcript once the result is saved, and the vendor removes uploaded audio on its retention schedule. Nothing is uploaded until you press Upload & transcribe. See the privacy policy for details.
How long does transcription take?
Usually a small fraction of the recording length. Jobs run asynchronously, so you can keep the tab open or reload the page later to pick the transcript back up. Long files take longer to upload on a slow connection.
Can I export a transcript to Word or PDF?
Yes. Choose DOCX for Word or Print / PDF to open the browser print dialog. TXT, SRT, VTT, and JSON downloads are also available.
Can I edit the text and keep the timestamps?
Yes. Each timestamped segment has its own editable text field. Your corrections carry over to every export.