Skip to main content
POST
/
v1
/
transcriptions
Transcribe Audio
curl --request POST \
  --url https://api.spi-tch.com/v1/transcriptions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form model=mansa_v1 \
  --form language=yo \
  --form 'url=<string>' \
  --form 'special_words=<string>' \
  --form timestamp=sentence \
  --form content=@example-file
{
  "request_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "text": "<string>",
  "timestamps": [
    {
      "text": "<string>",
      "start": 123,
      "end": 123
    }
  ]
}

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

multipart/form-data
​
language
enum<string>
required
Available options:
yo,
en,
ha,
ig,
am
​
model
enum<string> | null
default:legacy
Available options:
mansa_v1,
legacy,
human
​
content
​
url
string | null
​
special_words
string | null
default:""
​
timestamp
enum<string> | null
default:none
Available options:
sentence,
word,
none

Response

Transcription completed successfully. Returns the transcribed text with optional timestamps and metadata.

​
request_id
string<uuid>
required
​
text
string
required
​
timestamps
TimeStamp · object[] | null
⌘I