LEAPERone Docs

Audio Transcription

POST /v1/audio/transcriptions

The rapid model is temporarily unavailable. Please use whisper-1 instead.

Transcribe audio into text using the whisper-1 model.

Endpoint

POST https://api.leaper.one/v1/audio/transcriptions

Models

ModelProviderPricingDescription
rapidLEAPERone0.006 credits/minFast transcription (temporarily unavailable)
whisper-1OpenAI0.006 credits/minOpenAI Whisper model

Parameters

ParameterTypeRequiredDescription
filefileYesAudio file to transcribe (multipart upload)
modelstringNoModel to use: "rapid" or "whisper-1". Default: "rapid"
response_formatstringNoOutput format: "text", "json", or "verbose_json". Default: "json"
languagestringNoISO 639-1 language code (e.g. "en", "zh"). Improves accuracy if specified
promptstringNoHint text to improve transcription quality (whisper-1 only)
temperaturenumberNoSampling temperature between 0 and 1 (whisper-1 only)

Request

Using the default model (rapid)

curl -X POST https://api.leaper.one/v1/audio/transcriptions \
  -H "Authorization: Bearer sk-your-api-key" \
  -F file=@recording.mp3 \
  -F response_format=json

Using whisper-1

curl -X POST https://api.leaper.one/v1/audio/transcriptions \
  -H "Authorization: Bearer sk-your-api-key" \
  -F file=@recording.mp3 \
  -F model=whisper-1 \
  -F response_format=json

Response

{
  "text": "Hello, this is a sample transcription of the audio file."
}

When using verbose_json, the response includes word-level timestamps:

{
  "task": "transcribe",
  "language": "en",
  "duration": 42.5,
  "text": "Hello, this is a sample transcription of the audio file.",
  "words": [
    { "word": "Hello,", "start": 0.0, "end": 0.5 },
    { "word": "this", "start": 0.5, "end": 0.7 },
    { "word": "is", "start": 0.7, "end": 0.9 }
  ]
}

Supported Audio Formats

mp3, mp4, mpeg, mpga, m4a, wav, webm

File uploads are limited to 25 MB.

Notes

  • Billing is based on audio duration, charged at the per-model rate listed above.
  • If no model is specified, rapid is used by default.
  • Streaming (stream=true) is not supported at this time.