# Transcription models — KolWrite API

> Model ids for the `model` parameter of `POST https://app.kolwrite.com/transcribe`. Last updated 2026-10-08.

New integrations should use Base or the Oracle family. When `model` is omitted the API uses `core`, a legacy model, so always send it.

| Model | `model` value | Credits / audio hour | US$ / audio hour | US$ / minute | Translation (`translate_to`) | Use it for |
| --- | --- | --- | --- | --- | --- | --- |
| Base | `base` | 0.40 | US$0.48 | US$0.008 | no | Low-cost transcription, word timestamps and speaker separation for clear audio and high volume. |
| Oracle Mini | `oracle_mini` | 0.80 | US$0.96 | US$0.016 | yes | Fast Oracle tier; the lowest-priced model that can translate (translate_to). |
| Oracle | `oracle` | 1.20 | US$1.44 | US$0.024 | yes | Production transcription and multilingual work, with translation. |
| Oracle Pro | `oracle_pro` | 1.40 | US$1.68 | US$0.028 | yes | Premium Oracle quality for demanding production audio. |
| Oracle Max | `oracle_max` | 3.00 | US$3.60 | US$0.060 | yes | Maximum quality for difficult or high-stakes audio. |
| Core (legacy) | `core` | 1.00 | US$1.20 | US$0.020 | no | Legacy. Kept for existing integrations; it is the default when model is omitted. |
| Edge (legacy) | `edge` | 1.20 | US$1.44 | US$0.024 | no | Legacy. Previous-generation higher-accuracy model for existing integrations. |

Notes:

- Every model returns the same output formats (`json`, `txt`, `srt`) and supports regular diarization, Pro diarization and channel separation.
- Translation (`translate_to`) works only on `oracle_mini`, `oracle`, `oracle_pro`, `oracle_max`. Base, Core and Edge are transcription-only.
- Oracle Mini returns segment-level timestamps for plain transcription and enables word alignment automatically when a speaker mode (diarization or channel separation) is selected.
- Legacy: `core`, `edge` are maintained for existing integrations.
- Speech recognition accuracy varies with audio quality, language and domain. Test on your own recordings before choosing; KolWrite does not publish a per-language accuracy figure for this API.

## Add-ons

| Add-on | Credits per audio hour |
| --- | --- |
| Speaker diarization | 0.00 |
| Pro speaker diarization | 0.20 |
| Standard channel separation | included |

Overlapping-speech separation is billed at the selected model rate for the greater of the recording duration or the total detected speech time across its physical channels.

HTML: https://console.kolwrite.com/models