v2

latestOpenAPI 3.1.02026-08-0514431.6 KB

Transcribe audio

OpenAI-compatible multipart STT input. Speko rewrites or unwraps the request for eligible HTTP, WebSocket, or multi-step STT adapters and normalizes supported transcript shapes to {"text":"..."}; audio compatibility can narrow the candidate set. An exact ru language hint narrows the candidate set further: it routes only to compatible OpenAI transcription models.

post/v1/audio/transcriptions

Headers

X-Speko-Objective'latency' | 'quality' | 'cost' | 'balanced'

Routing objective. Defaults to the route policy.

X-Speko-Languagestring

BCP 47 language tag used for benchmark selection and provider transcription.

X-Speko-Allowstring

Comma-separated providers or provider:model ids to allow.

X-Speko-Denystring

Comma-separated providers or provider:model ids to exclude.

X-Speko-Max-Pricenumber

Maximum published benchmark price for the request stage: STT in USD per minute, LLM in USD per 1M tokens, or TTS in USD per 1M characters. Candidates without a published price are excluded when this constraint is set.

Response

Transcription

textstring