Transcriptions & Translations API

FastRouter provides endpoints for audio processing using the whisper-1 model. You can transcribe speech from supported audio files or translate foreign-language speech into English text.

Parameters

Parameter	Description
model	Must be "whisper-1"
file	Path to the audio file to upload
language	(Transcription only) ISO-639-1 code (e.g., "en", "es")
response_format	Output format (see above)
temperature	(Optional) Sampling temperature (higher = more random output)

Transcriptions API Request Format

Use this endpoint to convert spoken audio into written text in the original language of the audio. FastRouter supports various output formats and audio types.

Endpoint

POST /v1/audio/transcriptions

Supported Input File Formats

• MP3, MP4, MPEG, MPGA, M4A, WAV, WEBM

Request Example

curl --location 'https://go.fastrouter.ai/v1/audio/transcriptions' \
--header 'Authorization: Bearer API-KEY' \
--form 'model="whisper-1"' \
--form 'language="en"' \
--form 'file=@"/path/to/file.mp3"' \
--form 'response_format="verbose_json"'

Output Formats

Set response_format to one of the following:

• json – Basic structured response

• text – Plain text transcription

• srt – SubRip subtitle file

• vtt – WebVTT subtitle file

• verbose_json – Detailed metadata along with transcript

Translations API Request Format

Use this endpoint to translate audio from supported languages into English. The audio will be automatically transcribed and then translated.

Unlike /transcriptions, this endpoint always returns English text, regardless of the input language.

Endpoint

POST /v1/audio/translations

Request Example

curl --location 'https://go.fastrouter.ai/v1/audio/translations' \
--header 'Authorization: Bearer API-KEY' \
--form 'model="whisper-1"' \
--form 'file=@"/path/to/file.mp3"' \
--form 'response_format="verbose_json"' \
--form 'temperature="0.1"'