> ## Documentation Index
> Fetch the complete documentation index at: https://docs.kymaapi.com/llms.txt
> Use this file to discover all available pages before exploring further.

# GPT-4o mini Transcribe

> OpenAI premium STT on Kyma. Best accuracy on conversational audio, noisy backgrounds, and code-switching languages. $0.00405/min via the `transcribe-quality` alias.

## Overview

`gpt-4o-mini-transcribe-2025-12-15` is OpenAI's premium speech-to-text model, surfaced on Kyma through the `transcribe-quality` alias. It's the right pick when accuracy on real-world audio matters more than raw cost — conversational dialogue, noisy environments, and multilingual code-switching (Vietnamese ↔ English mixing, Mandarin ↔ English, etc.) where Whisper Turbo's distilled decoder gives ground.

Ships alongside the default `transcribe` alias (which resolves to [Whisper Large v3 Turbo](/models/whisper-v3-turbo)). Two aliases, one decision per request: pick `transcribe` for high-volume bulk transcription, `transcribe-quality` when accuracy is the constraint.

## Specs

| Field              | Value                                                                 |
| ------------------ | --------------------------------------------------------------------- |
| Model ID           | `gpt-4o-mini-transcribe-2025-12-15`                                   |
| Alias              | `transcribe-quality`                                                  |
| Creator / Provider | OpenAI                                                                |
| Best for           | Noisy / conversational / code-switching audio, multilingual dictation |
| Max file size      | 25 MB (multipart upload)                                              |
| Input modalities   | Audio (`mp3`, `wav`, `m4a`, `ogg`, `webm`, `flac`)                    |
| Output modalities  | Text                                                                  |
| Pricing mode       | Per minute                                                            |
| Min billable       | 1 minute (rounded up)                                                 |

## Pricing

|               |                           Cost |
| ------------- | -----------------------------: |
| Per minute    |                  **\$0.00405** |
| 1-hour file   |                        \$0.243 |
| 5-second clip | \$0.00405 (rounds up to 1 min) |

\~4.5× the cost of default Whisper Turbo (\$0.0009/min) — that's the premium you pay for OpenAI's accuracy on hard audio. For high-volume bulk transcription, default to `transcribe`; reserve `transcribe-quality` for the cases that need it.

## Use this when

* Audio contains code-switching (e.g. Vietnamese + English in the same utterance) and Whisper Turbo is producing garbled output on the non-primary language.
* Background noise, low-quality recording, or far-field microphones — accuracy matters more than throughput.
* Conversational dictation where capitalization, punctuation, and proper nouns must be right first time.

## Pick something else when

* High-volume bulk transcription where \~99% accuracy is fine — use [`whisper-v3-turbo`](/models/whisper-v3-turbo) at \~4.5× cheaper.
* The audio is over 25 MB — Quality tier currently only supports multipart upload. Use `transcribe` with the JSON `audio_url` mode for files up to 100 MB.
* You need transcription that reliably stays up under outage — the default `transcribe` alias has an automatic fallback chain, while the Quality tier surfaces a `5xx` directly (see below).

## No fallback

The default `transcribe` alias automatically retries through a fallback chain on upstream outage. The Quality tier **opts out** by design: you chose this model specifically for accuracy, and silently swapping to a different model would defeat that contract. Outages return as `502 transcription_failed` so your client knows to retry or downgrade.

See the [Fallback chain section](/api-reference/audio-transcriptions#fallback-chain) on the endpoint reference for the full rules.

## Concurrency limits

Counted against the **`transcription`** audio sub-pool, which is isolated from text-to-speech and audio understanding. Per-tier caps and the full sub-pool breakdown are on [Rate Limits — Audio limits](/guides/rate-limits#audio-limits-per-capability-sub-pools).

## Example

```bash theme={null}
curl -X POST https://kymaapi.com/v1/audio/transcriptions \
  -H "Authorization: Bearer $KYMA_API_KEY" \
  -F "file=@interview.mp3" \
  -F "model=transcribe-quality" \
  -F "response_format=verbose_json"
```

### Python (raw HTTP — OpenAI SDK doesn't expose Kyma aliases)

```python theme={null}
import os
import requests

with open("interview.mp3", "rb") as f:
    resp = requests.post(
        "https://kymaapi.com/v1/audio/transcriptions",
        headers={"Authorization": f"Bearer {os.environ['KYMA_API_KEY']}"},
        files={"file": f},
        data={"model": "transcribe-quality", "response_format": "verbose_json"},
    )
result = resp.json()
print(result["text"])
```

The Python OpenAI SDK pins to `whisper-1` internally for transcription so passing `model="transcribe-quality"` through the SDK won't reach Kyma's alias resolver. Raw `requests` works fine.

## Aliases that resolve here

* `transcribe-quality` — premium ASR tier on Kyma.

If you want stable behavior across alias changes, pin `gpt-4o-mini-transcribe-2025-12-15` directly. If you want to ride future Quality-tier upgrades (e.g. if Kyma promotes a newer OpenAI STT SKU), use the alias.

## See also

* [`whisper-v3-turbo`](/models/whisper-v3-turbo) — default STT (cheaper, faster, fallback chain enabled)
* [`POST /v1/audio/transcriptions`](/api-reference/audio-transcriptions) — endpoint reference
* [Rate Limits](/guides/rate-limits) — concurrency caps for the `openai` audio sub-pool
* [Model Aliases](/guides/model-aliases) — full alias index