Speech-to-Text

Audio transcription powered by Gemma4. Record from your mic or drop a file — it uploads straight to CuteDSL storage and transcribes from the resulting URL. Supports multiple languages.

$0.02 per minute

Parameters

Parameter	Type	Required	Default	Description
audio_url	string	required	—	URL of the audio file to transcribe. Use the recorder/uploader below, or pass any public mp3, wav, m4a, ogg or webm URL.

Example Request

# 1. Get a presigned upload URL (skip if your audio is already public)
curl "https://cutedsl.cc/api/uploads/presign?filename=speech.wav&content_type=audio/wav&dataset=stt" \
  -H "Authorization: Bearer YOUR_API_KEY"
# -> {"upload_url": "https://...r2.cloudflarestorage.com/...", "public_url": "https://appstatic.app.nz/cutedsl/uploads/..."}

# 2. PUT the file straight to storage (no proxy, no size limit on our API)
curl -X PUT "PRESIGNED_UPLOAD_URL" \
  -H "Content-Type: audio/wav" \
  --data-binary @speech.wav

# 3. Transcribe the public URL
curl -X POST https://cutedsl.cc/api/service \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "service": "stt",
    "audio_url": "https://appstatic.app.nz/cutedsl/samples/stt-sample-en.mp3"
  }'

Example Response

{
  "result": {
    "text": "Hello, this is a transcription example.",
    "language": "en",
    "duration_seconds": 15.3
  },
  "credits_used": 51,
  "credits_remain": 49949,
  "usd_equivalent": 0.051
}

Playground

Connect your wallet to try the playground.

Connect Wallet

Back to all services