Build with the Synora API

Quickstart

Three steps to your first transcription.

1. 1

   Create an account

   Sign up or sign in with Google, then open your account. API requests use your prepaid balance; guest trials have separate quotas.

2. 2

   Get an API key

   Open Developers → API tokens. Create a token, copy it once and keep it on your server. STT/TTS usage charges your balance; the token cannot manage your account or admin settings.

3. 3

   Send your first request

   Upload an audio file to the Speech to Text endpoint and get the transcript back as JSON.

curl https://synora-ai.uz/api/v1/stt/transcribe \
  -H "Authorization: Bearer $SYNORA_API_KEY" \
  -F "file=@meeting.wav" \
  -F "language=uz" \
  -F "model=gemini"

Authentication

Every request must include your API key in the Authorization header. Requests without a valid key return 401 Unauthorized.

Authorization: Bearer YOUR_API_KEY

Never put your API key in frontend code or a public repository. Call the API from your server and rotate the key in the dashboard if it leaks.

Endpoints

Base URL: https://synora-ai.uz/api/v1

Speech to Text

POST /stt — send an audio file as multipart/form-data and receive the transcript.

{
  "ok": true,
  "ai_session_id": "a80717ac-3c34-4938-9eae-ef6873f3ceca",
  "text": "Assalomu alaykum, qabulga yozilmoqchi edim.",
  "language": "uz",
  "audio_ms": 4820,
  "price_micros": 1500000,
  "price": "1.500000",
  "model": "gemini"
}

Errors

Errors use standard HTTP status codes and return a JSON body with a code and a human-readable message.