Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.destined.ai/llms.txt

Use this file to discover all available pages before exploring further.

​
Welcome to Destined Voice API

Destined Voice helps companies to evaluate voice models and agents with globally representative voices and custom AI models.

​
Why Destined Voice?

10,000+ Real Voices

Diverse demographics including gender, age, region, and accent. All voices are from consented speakers.

Voice Generation

Generate new custom voices for your evals.

Voice Agent Evals

Evaluate speech-to-text providers with WER/CER metrics and demographic bias analysis.

Batch Processing

Generate audio for multiple speakers asynchronously with job tracking.

​
Quick Example

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

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

// Generate speech
const audio = await client.ttsGeneration.synthesizeSpeechV1TtsSynthesizePost({
  speakerId: "speaker-uuid",
  text: "Hello, welcome to Destined Voice!",
});

console.log(audio.audioUrl);

​
Features

FeatureDescription
TTS SynthesisConvert text to natural speech using any speaker voice
Speaker BrowseFilter speakers by gender, age, region, accent
Batch JobsProcess multiple synthesis requests asynchronously
STT EvaluationEvaluate providers such as Deepgram, AssemblyAI, OpenAI, Google, Azure, Amazon, Soniox
Dataset ImportUpload CSV files for bulk TTS generation
Usage TrackingMonitor character usage and API calls

​
Next Steps

Quickstart

Get up and running in 5 minutes

API Reference

Explore all available endpoints