# Speaker-Labeled Transcript with Separated Tracks

AudioPod gives you a timestamped, speaker-labeled transcript alongside one audio track per speaker: turn on Include Speaker-Labeled Transcription in Speaker Separation and the AudioDiarize engine writes who said what. It costs no extra credits on any plan, including free Basic, beyond the 330 credits per minute for the separation.

Canonical URL: https://audiopod.ai/speaker-separation/speaker-labeled-transcript
Last updated: 2026-10-16

## Facts

| Fact | Detail |
| --- | --- |
| How to get it | Turn on Include Speaker-Labeled Transcription before you start the job |
| Extra cost | None — the job is 330 credits per minute either way |
| What it contains | Each turn with its speaker label and start and end time, aligned to the speaker tracks |
| Downloads | TXT (readable) and JSON (segments with timestamps) |
| Editing | Reassign a turn to an existing or a new speaker, correct the text, and merge, split or delete segments in the browser |
| Saved edits | Versioned on the job; over the API at PUT /api/v1/speaker/jobs/{id}/edit |
| Timeline only | POST /api/v1/speaker/diarize (API) returns who-spoke-when without audio tracks, at $0.20 per minute from the prepaid API wallet, or 1,500 credits per minute when paid from credits |
| Speaker labels | Generic labels in the editor; custom names only over the API (PUT /api/v1/speaker/jobs/{id}/edit with a speaker string per segment) |

## How to do it

1. Open Speaker Separation and add the recording.
2. Switch on Include Speaker-Labeled Transcription.
3. Start the job; the quote is the same with the transcript on.
4. Read the transcript next to the tracks and fix lines or speaker assignments in the editor.
5. Download the transcript as TXT or JSON, and each speaker's audio as WAV or MP3.

## Transcript here, or in Speech to Text?

- Here: you also want each person's audio — to edit a podcast, pull a quote in the speaker's own voice, or build a clean dataset per voice.
- Speech to Text: you only want words — subtitles (SRT, VTT), word-level timestamps or many files of text, with speaker labels too.
- Both read the same recording; there is no need to run one before the other.

## Fixing the transcript

- Move a line to the right speaker when two similar voices were confused, or to a new speaker the detector missed.
- Join turns that were cut mid-sentence, split one that holds two people, or delete a stray segment.
- Custom speaker names are set over the API: send each segment's speaker as any string to the edit endpoint.
- Each save is kept as a new version, so an edit can be checked against what came before.

## FAQ

**Does the speaker-labeled transcript cost extra?**
No. Speaker separation is 330 credits per minute with or without the transcript. The free Basic plan's 5,000 monthly credits cover about 15.1 minutes. See /pricing for plans.

**Can I rename the speakers in the transcript?**
Not in the browser editor: there you can reassign a turn to an existing speaker or add a new one, correct the text, and merge, split or delete segments, and each save is kept as a new version. Custom names such as a guest's real name are set over the API, by sending each segment's speaker as any string to PUT /api/v1/speaker/jobs/{id}/edit.

**What formats can I download the transcript in?**
TXT, for reading and pasting, and JSON, which keeps every segment's speaker and start and end time for your own tools.

**Can I get subtitles from it?**
For SRT or VTT subtitles use Speech to Text, which writes them directly and can label speakers too. Speaker Separation's transcript is built to sit next to the per-speaker audio.

**Can I get only who-spoke-when, without separate tracks?**
Yes, over the API: POST /api/v1/speaker/diarize returns the speaker timeline without writing a track per speaker. API calls are priced separately from the dashboard: $0.20 per minute from the prepaid API wallet, or 1,500 credits per minute when paid from credits.

## Related

- [Speaker Separation](https://audiopod.ai/features/speaker-separation) — The tool, the free demo and the speaker guides.
- [Speech to Text](https://audiopod.ai/features/speech-to-text) — Subtitles, word timestamps and transcripts on their own.
- [Long recordings](https://audiopod.ai/speaker-separation/long-recordings) — Length limits per plan and what an hour costs.
- [Speaker separation API](https://audiopod.ai/speaker-separation/api) — Endpoints, parameters and the MCP tool.

## Pricing

Plan prices: [pricing](https://audiopod.ai/pricing). Start: [Get a speaker-labeled transcript](https://audiopod.ai/auth/signup?callbackUrl=%2Fdashboard%2Ftools%2Fspeaker-separation).