Skip to main content

1. Get Your API Key

Sign up at destined.ai and get your API key from the dashboard.

2. Install the SDK

npm install @destined-ai/voice

3. Initialize the Client

import { SDK } from "@destined-ai/voice";

const client = new SDK({
  bearerToken: process.env.DESTINED_API_KEY,
});

4. Browse Speakers

Find the perfect voice for your use case:
// List female speakers from the US
const speakers = await client.speakers.listSpeakersV1SpeakersGet({
  gender: "Female",
  region: "United States",
  limit: 10,
});

console.log(speakers);
// [
//   { id: "abc123", gender: "Female", region: "Georgia", accent: "Southern" },
//   { id: "def456", gender: "Female", region: "California", accent: "General American" },
//   ...
// ]

5. Generate Speech

const result = await client.ttsGeneration.synthesizeSpeechV1TtsSynthesizePost({
  speakerId: "abc123",
  text: "Hello! This is a test of the Destined Voice API.",
});

console.log(result.audioUrl);
// https://destined-voice.s3.amazonaws.com/audio/xxx.wav

6. Track Batch Jobs

For multiple generations, use batch processing:
// Start a batch job
const job = await client.ttsGeneration.batchSynthesizeV1TtsBatchPost({
  items: [
    { speakerId: "abc123", text: "First sentence." },
    { speakerId: "def456", text: "Second sentence." },
    { speakerId: "ghi789", text: "Third sentence." },
  ],
});

console.log(job.jobId);
// "job_abc123"

// Check job status
const status = await client.jobs.getJobV1JobsJobIdGet({
  jobId: job.jobId,
});

console.log(status);
// { status: "completed", progress: 100, results: [...] }

Next Steps