# Speech-to-text transcription, one API key

Markdown version of https://kymaapi.com/transcription, for agents and crawlers. Same content as the HTML page.

- Generated: 2026-10-28T21:43:33.736Z
- HTML page: https://kymaapi.com/transcription
- Model catalog: https://kymaapi.com/models.md
- Pricing: https://kymaapi.com/pricing.md

Speech-to-text API

Transcribe audio to text fast and accurately, with timestamps and language detection. OpenAI Whisper-compatible, so existing Whisper code works by changing the base URL. Billed per second of audio (10-second minimum per request), with a multi-route fallback chain so transcription stays up.

- [Get free API key →](https://kymaapi.com/signup)
- [See pricing](https://kymaapi.com/pricing)

`POST /v1/audio/transcriptions` · $0.50 free credit on the free tier, no card

## 4 models, one API key

Switch models with a string. Billed per use, refunded on failure.

- [Whisper Large v3 Turbo · OpenAI · $0.0009 / min](https://kymaapi.com/models/whisper-v3-turbo)
- [GPT-4o mini Transcribe · OpenAI · $0.00405 / min](https://kymaapi.com/models/gpt-4o-mini-transcribe-2025-12-15)
- [GPT Transcribe · OpenAI · $0.006075 / min](https://kymaapi.com/models/gpt-transcribe)
- [Gemini 3.5 Transcribe · Google · $0.00675 / min](https://kymaapi.com/models/gemini-3.5-transcribe)

## Quick start

OpenAI-compatible. Point your client at `https://kymaapi.com/v1` with a ky- key.

```
curl https://kymaapi.com/v1/audio/transcriptions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F model="whisper-v3-turbo" \
  -F file="@meeting.mp3"
# Returns: { "text": "..." }  (use response_format=verbose_json for timestamps)
```

## FAQ

### Which transcription models does Kyma support?

Kyma offers Whisper Large v3 Turbo as the default speech-to-text model, fast and inexpensive, plus a premium transcription option for higher accuracy on conversational or code-switching audio. Both use the OpenAI Whisper request shape.

### Is the transcription API OpenAI Whisper-compatible?

Yes. Call POST /v1/audio/transcriptions as a multipart upload with a model and file, exactly like the OpenAI audio transcriptions API. Existing Whisper code works by pointing the base URL at https://kymaapi.com/v1.

### How much does transcription cost?

Transcription is billed per second of audio processed, with a 10-second minimum per request. The default Whisper model costs a fraction of a cent per minute. See the pricing page for exact rates.

### Can I get word- or segment-level timestamps?

Yes: request response_format=verbose_json to receive segment timestamps and detected language alongside the transcript.

- [All models](https://kymaapi.com/models)
- [Pricing](https://kymaapi.com/pricing)
- [Compare](https://kymaapi.com/compare)
- [Transcription API docs →](https://docs.kymaapi.com/api-reference/audio-transcriptions)

$0.50 free credit on the free tier. No card required.

[Get your free API key →](https://kymaapi.com/signup)