Skip to main content
POST
/
transcribe
/
speech-to-text
Transcribe audio file
curl -X POST "https://api.upliftai.org/v1/transcribe/speech-to-text" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "file=@/path/to/audio.mp3" \
  -F "model=scribe" \
  -F "language=ur"
{
  "text": "آج کا موسم کیسا ہے؟ میں نے سنا ہے کہ بارش ہونے والی ہے۔"
}
This API is currently in beta. Features and pricing may change.
{
  "text": "آج کا موسم کیسا ہے؟ میں نے سنا ہے کہ بارش ہونے والی ہے۔"
}

Authorizations

​
Authorization
string
header
required

API key with format "Bearer sk_api_..."

Body

multipart/form-data
​
file
file
required

Audio file to transcribe (max 25MB)

​
model
enum<string>
default:scribe

AI model to use

Available options:
scribe,
scribe-mini
​
language
enum<string>
default:ur

Language of the audio

Available options:
ur
​
domain
enum<string>

Domain-specific optimization

Available options:
phone-commerce,
farming

Response

Successful transcription

Response from speech-to-text transcription

​
text
string

Transcribed text from the audio