# GPT Transcribe

> Speech-to-text. OpenAI's current premium STT and the replacement for the gpt-4o-transcribe family — high real-world accuracy on conversational audio, noisy backgrounds, and code-switching (Vi/En etc).

Human version: https://kymaapi.com/models/gpt-transcribe
Live JSON: `GET https://kymaapi.com/v1/models` (no auth required)

## Facts

- **Model ID**: `gpt-transcribe`: pass this as `model` in the request body
- **Creator**: OpenAI
- **Released**: 2026-08-26
- **Price**: $0.00607 / minute

## Call it

```bash
curl https://kymaapi.com/v1/audio/speech \
  -H "Authorization: Bearer $KYMA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "gpt-transcribe", "prompt": "..."}'
```

## Positioning

OpenAI's current premium speech-to-text model, and the id OpenAI names as the replacement for the gpt-4o-transcribe family. Pin `gpt-transcribe` on POST /v1/audio/transcriptions.

## About

GPT Transcribe converts recorded audio into text. It targets the hard cases rather than clean studio audio: conversational speech, several speakers, background noise, and sentences that switch language mid-way (Vietnamese and English in one pass, for example).

On Kyma it is served through the same OpenAI-compatible transcription endpoint as the other speech-to-text SKUs — multipart `file` or JSON `audio_url`, with `json` and `text` response formats. Billing is per minute of audio, rounded up, with a one-minute minimum; the exact figure comes back in the response and in the X-Kyma-Cost-USD header.

This is file transcription. It is not the live streaming surface, and it is not audio-scene understanding. It returns a transcript, not segment timestamps, so subtitle work stays on whisper-v3-turbo.

## Use cases

- **Conversational audio transcription**, Captures multi-speaker dialogue and natural speech patterns with high accuracy.
- **Noisy background dictation**, Filters background interference to produce clean text from field recordings or calls.
- **Mixed language audio processing**, Handles code-switched audio streams like Vietnamese and English in a single pass.
- **Migration off the gpt-4o-transcribe family**, The id OpenAI names as the replacement for the models it shuts down on 2027-02-26.

## Not ideal for

Do not use this model for generating audio, for live bidirectional speech, or when you need segment timestamps — it does not return them, and SRT/VTT output needs a model that does.

## Pick something else when

- You need segment timestamps, SRT or VTT output, or the cheapest per-minute rate on clear recordings → `whisper-v3-turbo`
- You want a file-transcription SKU from a different creator → `gemini-3.5-transcribe`

## See also

- All models: https://kymaapi.com/models.md
- Pricing: https://kymaapi.com/pricing.md
- Other models by OpenAI: https://kymaapi.com/models?q=OpenAI