PindoDocs
Web AppWeb

Quickstart

Transcribe your first audio clip in two minutes with no token required. Public endpoints let you try every model straight away.

Pick an endpoint

Append /public to call a model without authentication. We'll transcribe Kinyarwanda audio with Speech-to-Text.

POST/ai/stt/rw/public

Send your audio

Post the file as multipart form data. Supported formats include mp3, wav, ogg, flac, and more.

# Public access (rate-limited, no token)
curl -X POST "https://api.pindo.io/ai/stt/rw/public" \
     -F "audio=@/path/to/your/file.mp3"

# Authenticated access
curl -X POST "https://api.pindo.io/ai/stt/rw" \
     -H "Authorization: Bearer YOUR_ACCESS_TOKEN" \
     -F "audio=@/path/to/your/file.mp3"

Read the transcript

You'll get back the recognized text and a URL to your uploaded audio.

{
  "code": 200,
  "data": {
    "text": "...", 
    "uploaded_audio_url": "path/file_name.mp3"
  },
  "error": null,
  "object": "stt",
  "status": "success"
}

Go to production

Drop the /public suffix and add a bearer token for higher limits.

Authorization: Bearer YOUR_ACCESS_TOKEN