Providers and ModelsOpenAI

OpenAI-Whisper-1

OpenAI-Whisper-1

Provider: OpenAI
Category: Transcription
Endpoint: POST /v1/audio/transcriptions
Context window: —
Served from: —

Whisper-1 speech-to-text transcription trained on multilingual supervised audio, with a 25 MB upload limit per file.

At a glance

FieldValue
Model idopenai-whisper-1
Input modalitiesaudio
Output modalitiestext
Context window—
Region—
Featurestranscription, speech_to_text
NewNo
Native inferenceNo

Pricing

ChargeSpecRate
Per Minute of Audiofixed$0.030

Example request

$curl https://api.empiriolabs.ai/v1/audio/transcriptions \
>  -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
>  -F model=openai-whisper-1 \
>  -F file=@meeting.mp3

Parameters

ParameterTypeRequiredDefaultDescription
filestringyes—Audio file (multipart upload) OR use file_url for the JSON path.
file_urlstringno—Public URL to fetch audio from (alternative to file upload).
translatebooleannofalseIf true, route to /audio/translations and translate to English instead of transcribing in source language.
timestampsbooleannofalseConvenience toggle. If true, sets response_format=verbose_json and includes word-level timestamp_granularities.
languagestringno—Optional ISO-639-1 language code. Auto-detected if omitted. Ignored when translate=true.
promptstringno—Glossary or prior context to bias the model.
response_formatenumno"json"Overridden to verbose_json when timestamps=true. · Allowed: json, text, srt, verbose_json, vtt
temperaturenumberno0Sampling temperature. · Range: 0 – 1
timestamp_granularitiesstringno—Comma-separated list: word, segment. Used when response_format=verbose_json.

Live machine-readable schema is also available at GET https://api.empiriolabs.ai/v1/models/openai-whisper-1.