Skip to main content
POST
/
api
/
content
/
transcribe
cURL
curl --request POST \
  --url https://recoup-api.vercel.app/api/content/transcribe \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --data '
{
  "audio_urls": [
    "<string>"
  ],
  "language": "en",
  "chunk_level": "word",
  "diarize": false,
  "model": "<string>"
}
'
{
  "audioUrl": "<string>",
  "fullLyrics": "<string>",
  "segments": [
    {
      "start": 123,
      "end": 123,
      "text": "<string>"
    }
  ],
  "segmentCount": 123
}

Authorizations

x-api-key
string
header
required

Your Recoup API key. Learn more.

Body

application/json

Audio transcription parameters

audio_urls
string<uri>[]
required

Audio file URLs to transcribe

Minimum array length: 1
language
string
default:en

Language code for transcription (e.g. en, es, fr). Defaults to en.

chunk_level
enum<string>
default:word

Granularity of timestamp chunks. Defaults to word-level.

Available options:
none,
segment,
word
diarize
boolean
default:false

Enable speaker diarization. Defaults to false.

model
string

fal.ai model ID. Defaults to fal-ai/whisper

Response

Song transcribed successfully

audioUrl
string
required

URL of the transcribed audio

fullLyrics
string
required

Complete transcribed lyrics as a single string

segments
object[]
required

Timestamped lyric segments

segmentCount
number
required

Total number of segments returned