Interview transcription with speaker labels
Transcribe a recorded interview with optional speaker labels, rename the speakers, and export a timestamped transcript as DOCX, text or captions.
Daily processing allowance
Checking current allowance...
Uploaded and processed audio is stored on SoundHalo. Audio access expires after 30 days (longer on paid plans, up to a year); expiry does not confirm storage deletion. Delete the stored files here before leaving this page. Speech providers have their own retention policies. Privacy policy.
Uploads use an external speech provider. Public transcription accepts 100 MB and 30 minutes per file, with 60 audio minutes per shared network per UTC day. Users on the same IPv4 address or IPv6 /64 share this allowance. A separate processing-cost budget also limits repeated jobs. Speaker labels are optional and need review.
Output presets
Only settings are saved locally. Recordings and transcripts are not saved here; download your work before leaving this page.
Speaker labels are a draft
Speaker labels group speech by voice and timing. They do not know who is speaking, so rename each label after listening. Check short replies, interruptions and crosstalk, where labels are most often wrong. Up to four distinct speakers are supported. If the speech provider returns no labels, the transcript shows a warning rather than guessing.
Separate microphones are easier
If each person had their own microphone recorded on its own channel, split the stereo file into two mono files first. Each file then has one known speaker. This does not work if the voices were already mixed into one channel.
For research interviews
Qualitative research usually needs timestamps, consistent speaker names and a document you can code. Export DOCX with timestamps, then check the transcript against the recording before analysis. Check your consent terms or ethics approval before uploading recordings to a cloud service. The privacy answer below explains where audio is processed and stored.
Related tools
Free to start, Pro for longer files
- No account: try a short recording. This allowance is shared by everyone on your network and by all anonymous visitors, so it can run out for the day.
- Free account: 3 files a day, up to 30 minutes each, with transcript history in your workspace.
- Pro: 50 files a day and files up to 10 hours.
Guides
FAQ
Where is the audio processed? +
The recording is uploaded to SoundHalo and sent to an external speech provider. SoundHalo stores uploaded audio. Access expires after 30 days (longer on paid plans, up to a year), which is not proof of storage deletion. Use Delete stored audio before leaving the page to remove SoundHalo files sooner. Provider copies and saved account transcripts have separate retention. Review the privacy policy before uploading sensitive recordings.
What are the limits? +
Public transcription accepts up to 100 MB and 30 minutes per file, with a daily limit of 60 audio minutes per shared network. Users on the same IPv4 address or IPv6 /64 share this allowance. A separate processing-cost budget can limit repeated short jobs. Daily budgets reset at midnight UTC. Signed-in plan limits differ. Long recordings may take several minutes.
Can I trust every speaker label? +
No. Treat labels as a draft and check them by listening. Very short turns, crosstalk and similar voices can be assigned to the wrong speaker.