Audio Transcription Guide

Learn how to transcribe audio with LEAPERone by uploading files or passing file URLs, language hints, and response formats.

The Audio Transcription endpoint converts speech to text. You can upload an audio file or pass a URL.

Models

Model	Pricing	Best for
`rapid` (default)	0.006 credits/min	Fast, general-purpose transcription
`whisper-1`	0.006 credits/min	High accuracy with prompt support

Quick Start

POST /v1/audio/transcriptions

curl -X POST https://api.leaper.one/v1/audio/transcriptions \
  -H "Authorization: Bearer sk-your-api-key" \
  -F [email protected]

Response

{
  "text": "Welcome to today's meeting. Let's start with the agenda..."
}

Using file_uri

Instead of uploading a file, you can pass a URL. This is recommended for large files or when your audio is already hosted online.

Transcribe from URL

curl -X POST https://api.leaper.one/v1/audio/transcriptions \
  -H "Authorization: Bearer sk-your-api-key" \
  -F file_uri=https://example.com/podcast-episode.mp3 \
  -F language=en \
  -F response_format=verbose_json

file_uri supports any publicly accessible audio URL. Formats include mp3, opus, m4a, wav, and more. No file size limit when using URL.

Choosing a Model

rapid (default)

Best for quick transcription without extra configuration. No model parameter needed. Supports language and prompt parameters.

Using rapid

curl -X POST https://api.leaper.one/v1/audio/transcriptions \
  -H "Authorization: Bearer sk-your-api-key" \
  -F [email protected] \
  -F language=zh \
  -F response_format=json

whisper-1

OpenAI's Whisper model. Supports prompt to improve recognition of specific terms and verbose_json for word-level timestamps.

Using whisper-1 with prompt

curl -X POST https://api.leaper.one/v1/audio/transcriptions \
  -H "Authorization: Bearer sk-your-api-key" \
  -F [email protected] \
  -F model=whisper-1 \
  -F response_format=verbose_json \
  -F prompt="LEAPERone, API, transcription"

Supported Formats

Format	Extension
MP3	`.mp3`
MP4	`.mp4`
MPEG	`.mpeg`, `.mpga`
M4A	`.m4a`
WAV	`.wav`
WebM	`.webm`
Opus	`.opus`

Response Formats

Set response_format to control the output:

Value	Description
`json`	JSON object with a `text` field (default).
`text`	Plain text transcription.
`verbose_json`	JSON with timestamps, segments, and metadata.
`srt`	SubRip subtitle format.
`vtt`	WebVTT subtitle format.

Billing is based on audio duration. See the API Reference for per-model pricing.

On this page