Developers

One API for every audio task

Predictable REST endpoints, signed webhooks and scoped keys — so voice becomes a feature of your product, not a project.

Request API accessSee pricing
API categories

Endpoints for the whole platform

Voice API

Generate speech at scale.

  • Streaming audio
  • Voice selection
  • Emotion controls

Podcast API

Programmatic episode creation.

  • Script generation
  • Multi-speaker
  • RSS output

Call API

Launch and manage voice agents.

  • Inbound & outbound
  • Live transcripts
  • Call events

Translation API

Translate audio content.

  • 100+ languages
  • Voice-matched
  • Batch jobs

Transcription API

Speech-to-text at scale.

  • Speaker labels
  • Timestamps
  • SRT output

Webhooks

React to events as they happen.

  • Job completed
  • Call ended
  • Signed payloads
Quick start

Your first request

Create a key in your workspace, call the speech endpoint and stream the audio straight back to your users.

  • Scoped API keys per environment
  • SDKs for JavaScript, Python and Go
  • Signed webhooks for long-running jobs
POST /v1/speech
curl https://api.sonicvanta.com/v1/speech \
  -H "Authorization: Bearer $SONICVANTA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "voice": "aria",
    "language": "en-US",
    "style": "narration",
    "text": "Welcome to SonicVanta."
  }' --output welcome.mp3

Building with voice?

Get API access and a walkthrough of the endpoints you need.

Book DemoSee pricing