> ## 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.

# TTS Generation

> Generate high-quality speech from text

## Overview

Destined Voice uses advanced neural TTS models to generate natural-sounding speech from any speaker in our library.

## Single Synthesis

Generate audio for a single text:

```typescript theme={null}
const result = await client.ttsGeneration.synthesizeSpeechV1TtsSynthesizePost({
  speakerId: "speaker-uuid",
  text: "Hello, this is a test.",
});

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

## Batch Synthesis

Generate multiple audio files in one request:

```typescript theme={null}
const job = await client.ttsGeneration.batchSynthesizeV1TtsBatchPost({
  items: [
    { speakerId: "speaker-1", text: "First sentence." },
    { speakerId: "speaker-2", text: "Second sentence." },
    { speakerId: "speaker-3", text: "Third sentence." },
  ],
});

// Returns a job ID to track progress
console.log(job.jobId);
```

## Audio Format

Generated audio uses these specifications:

| Property    | Value     |
| ----------- | --------- |
| Format      | WAV       |
| Sample Rate | 24,000 Hz |
| Bit Depth   | 16-bit    |
| Channels    | Mono      |

## Usage Tracking

Monitor your character usage:

```typescript theme={null}
const usage = await client.users.getUsageV1UsersUsageGet();

console.log(usage);
// {
//   characters_used: 45000,
//   characters_limit: 100000,
//   requests_today: 150,
//   period_start: "2024-01-01",
//   period_end: "2024-01-31"
// }
```

## Best Practices

<AccordionGroup>
  <Accordion title="Batch similar requests">
    Group multiple synthesis requests into batch jobs for better performance.
  </Accordion>

  <Accordion title="Preprocess text">
    Clean and normalize text before synthesis. Remove special characters and format numbers as words.
  </Accordion>

  <Accordion title="Cache audio">
    Store generated audio URLs. Re-synthesis of the same text with the same speaker produces identical audio.
  </Accordion>

  <Accordion title="Handle long text">
    For text longer than the character limit, split into sentences and combine audio files.
  </Accordion>
</AccordionGroup>