Create transcription | OpenRouter

Transcribes audio into text. Accepts base64-encoded audio input and returns the transcribed text.

AuthorizationBearer

API key as bearer token in Authorization header

This endpoint expects an object.

input_audioobjectRequired

Base64-encoded audio to transcribe

modelstringRequired

STT model identifier

languagestringOptional

ISO-639-1 language code (e.g., “en”, “ja”). Auto-detected if omitted.

providerobjectOptional

Provider-specific passthrough configuration

temperaturedoubleOptional

Sampling temperature for transcription

Transcription result

textstring

The transcribed text

usageobject

Aggregated usage statistics for the request

400

Bad Request Error

401

Unauthorized Error

402

Payment Required Error

404

Not Found Error

429

Too Many Requests Error

500

Internal Server Error

502

Bad Gateway Error

503

Service Unavailable Error

$	curl -X POST https://openrouter.ai/api/v1/audio/transcriptions \
>	-H "Authorization: Bearer <token>" \
>	-H "Content-Type: application/json" \
>	-d '{
>	"input_audio": {
>	"data": "UklGRiQA...",
>	"format": "wav"
>	},
>	"model": "openai/whisper-large-v3",
>	"language": "en"
>	}'

1	{
2	"text": "Hello, this is a test of OpenAI speech-to-text transcription.",
3	"usage": {
4	"cost": 0.000508,
5	"input_tokens": 83,
6	"output_tokens": 30,
7	"seconds": 9.2,
8	"total_tokens": 113
9	}
10	}

$	curl -X POST https://openrouter.ai/api/v1/audio/transcriptions \
>	-H "Authorization: Bearer <token>" \
>	-H "Content-Type: application/json" \
>	-d '{
>	"input_audio": {
>	"data": "UklGRiQA...",
>	"format": "wav"
>	},
>	"model": "openai/whisper-large-v3",
>	"language": "en"
>	}'

1	{
2	"text": "Hello, this is a test of OpenAI speech-to-text transcription.",
3	"usage": {
4	"cost": 0.000508,
5	"input_tokens": 83,
6	"output_tokens": 30,
7	"seconds": 9.2,
8	"total_tokens": 113
9	}
10	}