Who said what, in the summary and quotes

Transcription with speakers named in the summary and quotes.

Drop an interview, meeting or panel recording (files over 500 MB continue on the upload page). Speakers are identified and named in the summary, key quotes and chapters, and every line of the transcript carries a timestamp you can click to hear that moment. The opening minutes are a free preview; packs from $4 for 300 minutes, credits never expire.

Speakers named in summary & quotes Word-level timestamps TXT/DOCX/SRT/VTT/JSON Up to 10 hours or 5 GB per file

How it works

From a recording to who said what in three steps.

Nothing to install and no setting to switch on: the summary, key quotes and chapters name the speakers on every recording.

1

Upload the recording

A two-person interview, a team call or a panel. Up to 10 hours or 5 GB per file; the box here takes files up to 500 MB and larger ones continue on the upload page.

2

Speakers are named

The summary, key quotes and chapters say who said what, by name where the recording gives one. The transcript carries word-level timestamps.

3

Check and export

Click a timestamp to hear any line, search for a word, then download TXT, DOCX, SRT, VTT or JSON.

What you get

Who said what, without reading the whole transcript.

A plain transcript is one long block of words. The summary and key quotes give the conversation its shape, with each point tied to the person who made it.

Speaker-attributed quotes

Each key quote carries the name of the person who said it and the moment it was said. A 45-minute interview becomes a page of attributed quotes you can scan in minutes.

Named from the conversation

Names come from what is said: introductions, people addressing each other, the roles they speak in. Saying names at the start of a recording makes the attribution clearer.

A summary that says who argued what

The summary and chapters attribute points and positions to the people who made them, so a meeting or panel reads as who proposed, who objected and who agreed.

Timestamps to check every quote

Every line of the transcript carries its time in the recording. Click it to hear the moment before you publish a quote or an attribution.

Honest limits

When attribution needs a second look.

Naming speakers works best on clear recordings where people say who they are. These are the cases to check by clicking the timestamp and listening.

Crosstalk

When two people talk over each other, the words usually come through, but a quote from that moment can be attributed to the wrong person. Check heated moments and quick interruptions.

Names never said

If nobody says their name or role, there is less to name them by. A quick round of introductions at the start of a recording helps.

Very short turns

One-word replies such as yes, right or mm-hm carry little context, so agreement in a fast exchange is the easiest thing to misattribute.

The room and the microphone

A microphone per person, less echo and fewer people talking at once all help. One phone in the middle of a table of eight is the hardest case.

Pricing

Speakers named in the summary at the base price.

$4 buys 300 minutes, $18 buys 3,000 minutes and $32 buys 6,000 minutes, about $0.32 to $0.80 per audio hour. The summary, key quotes and chapters come with every transcript, and credits never expire.

A 1-hour interview uses $0.80 of credit on the $4 pack. A 3-hour panel uses $2.40 on the $4 pack, $1.08 on the $18 pack or about $0.96 on the $32 pack. Full details are on the pricing page.

$4 for 300 min $4 for 300 min $18 for 3,000 min $32 for 6,000 min Credits never expire

FAQ

Speakers and attribution, answered.

How does WhipScribe show who said what?

Speakers are identified and named in the summary, key quotes and chapters, so each key quote carries the name of the person who said it and the summary attributes points to people. The transcript itself carries a timestamp on every line, so you can check any attribution against the audio.

How do I get speakers named?

Upload the recording to the box on this page. The summary, key quotes and chapters name the speakers automatically, with nothing to switch on. The opening minutes are a free preview; a pack from $4 (300 minutes) opens the full transcript.

Are the lines of the transcript labelled by speaker?

The transcript lines carry timestamps rather than names; the speaker attribution lives in the summary, key quotes and chapters. If your document needs a name on every line, add them in any editor after downloading.

How are the speakers named?

From what is said in the recording: introductions, people addressing each other by name, and the roles they speak in. Saying names at the start of a recording makes the attribution clearer. Click the timestamp of a quote and listen before you publish an attribution.

Does it work for interviews and meetings?

Yes. Interviews, meetings and panels all get a summary, key quotes and chapters with the speakers named; check attributions where people interrupt each other. For interview tips see transcribe an interview.

Can I correct the transcript?

On your own transcripts you can edit the wording of a line or delete a line in the transcript view, then save. Downloads then use your edited version.

What does it cost?

$4 for 300 minutes, $18 for 3,000 minutes or $32 for 6,000 minutes, about $0.32 to $0.80 per audio hour, with the summary, key quotes and chapters included. Credits never expire.

How long can the recording be?

Up to 10 hours or 5 GB per file. The box on this page takes files up to 500 MB; larger files continue on the upload page.

Drop a recording. See who said what.

The opening minutes are a free preview, with the speakers named in the summary. A free account keeps your transcripts in one searchable library.

Looking for a transcription service?

For the recordings you have now: see our transcription service with prices and turnaround and an audio transcription service that takes links or files.