Sonna
API ReferenceText-to-Speech ModelsGoogle Cloud

Wavenet

Google Cloud WaveNet — neural voices with broad language support, available on all plans.

DeepMind WaveNet voices — same quality tier as Neural2 but with broader language coverage, including Indonesian, Chinese, Russian, and Turkish. Free-plan accessible.

EndpointPOST /api/v1/tts/synthesize
Model ID (ttsModel)google-wavenet
ProviderGoogle Cloud (Free + paid)
Character Limit3,000 (Free plan: 1,000)
Cost500 / 1K chars

Shared conventions

Auth, the voice→provider rule, rate limits, and the full error table live on the Speech API page. Below is only what's specific to Wavenet.

Model-specific notes

  • Extra languages vs Neural2 — Indonesian, Chinese, Russian, Turkish, and more.
  • Works on every plan, including Free (1,000 chars/request on Free).
  • Supports speed and pitch. Language is fixed by the voice (e.g. id-ID-Wavenet-A) — pick a voice in the language you need; there is no language-override.

Request body

ParameterTypeRequiredDescription
textstringYesText to synthesize (max 3,000 chars)
voicestringYesA Google Cloud voice ID from GET /api/v1/tts/voices
ttsModelstringYesMust be "google-wavenet"
speednumberNoSpeaking rate 0.254.0 · Default: 1.0
pitchnumberNoPitch 0.01.0 (maps to −20…+20 semitones; 0.5 = neutral) · Default: 0.5
titlestringNoTitle for the saved project
{
  "text": "Terima kasih telah menggunakan layanan kami.",
  "voice": "voice-uuid-wavenet-id",
  "ttsModel": "google-wavenet",
  "speed": 1.1
}

Response (200 OK)

{
  "url": "https://cdn.sonnalabs.app/sonna/api-ephemeral/tts/free/user123/stu901.mp3",
  "remainingCredits": 9750,
  "projectCreated": true
}

Errors (400 TEXT_TOO_LONG — 3,000, or 1,000 on Free — plus 402, 409, 429, 503) follow the shared Speech API table. No 403: Google voices are available to everyone.

On this page