VocenzaDocs

Quickstart

From zero to your first synthesized sentence in three steps.

This guide synthesizes a line of speech and saves it to a file. You will need an API key — create one from the Playground.

1

Export your key

Store the key in your environment so it never ends up in source control.

export VOCENZA_API_KEY="voc_..."
2

Synthesize speech

Send text to the /speech endpoint and write the streamed audio to disk.

curl https://api.vocenza.com/v1/speech \
  -H "Authorization: Bearer $VOCENZA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "vocenza-tts-1",
    "voice": "aria",
    "input": "Hi there — welcome to Vocenza."
  }' \
  --output hello.mp3
3

Play it back

Open hello.mp3 in any audio player. That's your first Vocenza request.

Next: go realtime

Batch synthesis is great for narration. For live agents, switch to the Realtime API — it streams audio both ways over a single websocket with barge-in support.

What's next