Text-to-Speech

Overview

Dotclone's Text-to-Speech (TTS) engine lets you convert text into human-like speech instantly. Whether you're building voice agents, creating audio content, or adding speech to your app, TTS provides:

The Text-to-Speech interface in Dotclone

How to Generate Speech

Follow these steps to generate your first speech audio:

1

Enter Your Text

Type or paste the text you want to convert.

Navigate to Text-to-Speech in the sidebar. Enter your text in the large input area. You can enter anything from a single sentence to multiple paragraphs.

Enter your text in the input area

2

Select a Provider

Choose your preferred TTS provider.

Click on the provider dropdown and select from the available options. Each provider has unique voice qualities and features.

Choose your TTS provider

3

Choose a Voice

Select a voice that fits your needs.

Browse the available voices for your selected provider. You can preview voices before selecting. Each provider has its own set of built-in voices.

Browse and select a voice

Preview a voice before selecting

4

Generate & Download

Create your audio and save it.

Click the Generate button. Once complete, you can play the audio, download it, or share it.

Click Generate to create your audio

Download or share your generated audio

Writing Better Text for TTS

The quality of your output depends heavily on how you write your input text. Here are tips for better results:

Example of well-formatted text for TTS

Providers

Dotclone integrates with multiple TTS providers. Each provider has its own voices, models, and settings. Choose based on your quality, speed, and cost requirements.

Select a provider from the dropdown

Each provider has multiple models to choose from

Voices

Each provider offers a unique set of built-in voices. Browse, preview, and select the voice that best fits your use case.

Built-in Voices

Built-in voices are pre-trained voices provided by each TTS provider. They cover various genders, accents, ages, and speaking styles.

Browse available voices for your selected provider

View voice details including language and style

Selecting a Voice

Click on any voice to select it. You can preview the voice by clicking the play button next to each voice name before making your selection.

Click to select a voice

Voice Cloning

Clone any voice with just 10-30 seconds of audio. Cloned voices can be used with any TTS provider in Dotclone.

How to Clone a Voice

1

Go to Voice Cloning

Navigate to the Voice Cloning section.

Click Voice Cloning in the sidebar

2

Upload Audio Sample

Upload 10-30 seconds of clear audio.

For best results, use audio that is:

• Clear speech without background noise
• Single speaker only
• 10-30 seconds in length
• Natural speaking pace (not reading)

Upload your audio sample

3

Name Your Voice

Give your cloned voice a descriptive name.

Enter a name for your cloned voice

4

Clone & Use

Process the voice and start using it.

Click Clone Voice to process. Once complete, your cloned voice will appear in the voice dropdown when using TTS.

Your cloned voice is ready to use

Select your cloned voice in the TTS interface

Deleting a Cloned Voice

To delete a cloned voice, go to Voice Cloning, find the voice you want to remove, and click the Delete button.

Click the delete button to remove a cloned voice

Enhance & Emotion

Add emotions, expressions, and style to your generated speech. Make your audio more engaging and natural-sounding.

Using Emotion Brackets

Add emotion tags in square brackets directly in your text. The TTS engine will interpret these and apply the corresponding emotion to the speech.

[emotion] Your text here

[excited] Wow, this is amazing! [laughs] I can't believe it worked! [whispers] Don't tell anyone...

[sad] I'm sorry to hear that happened.

[angry] This is completely unacceptable!

[cheerful] Good morning! How can I help you today?

Add emotion brackets directly in your text

Use the Enhance button for automatic emotion suggestions

Provider Settings

Each provider and model has specific settings you can adjust to fine-tune your audio output.

Adjust provider-specific settings in the settings panel

Use sliders to fine-tune your audio output

Sound Effects & Background Noise

Add ambient sounds and background noise to make your audio more immersive. This feature is available for MiniMax provider only.

Available Background Sounds

Choose from a variety of ambient sounds to mix with your generated speech:

Select a background sound from the dropdown

Adjust the mix level between speech and background

Supported Languages

Dotclone TTS supports over 50 languages and accents across all providers. Language availability may vary by provider and voice.

Select language when choosing a voice

Output Formats

Choose your preferred audio format when generating or downloading speech.

Select your preferred output format before downloading

TTS History

Every speech you generate is automatically saved to your history. Access, replay, or download any previously generated audio.

Accessing Your History

Click the History tab in the TTS interface to view all your previously generated audio files.

Click the History tab to view past generations

Browse your generated audio history

History Features

• Replay: Listen to any previous generation
• Download: Download the audio file again
• Copy Text: Copy the original text used
• Regenerate: Generate again with same or different settings
• Delete: Remove from history

Actions available for each history item

API Usage

Generate speech programmatically using the Dotclone API or SDK.

from dotclone import Dotclone

client = Dotclone()

# Generate speech
audio = client.tts.generate(
    text="Hello! Welcome to Dotclone.",
    provider="elevenlabs",
    model="eleven_v3",
    voice="emma",
    settings={
        "stability": 75
    }
)

# Save the audio
audio.save("welcome.mp3")

# Or get the URL
print(audio.url)

# Using emotion brackets
audio = client.tts.generate(
    text="[excited] Wow, this is amazing! [laughs] I love it!",
    provider="elevenlabs",
    model="eleven_v3",
    voice="emma"
)

audio.save("excited_speech.mp3")

# Use your cloned voice
audio = client.tts.generate(
    text="This is my cloned voice speaking.",
    provider="elevenlabs",
    voice="my-cloned-voice-id"  # Your cloned voice ID
)

audio.save("cloned_voice.mp3")

import Dotclone from 'dotclone';

const client = new Dotclone();

// Generate speech
const audio = await client.tts.generate({
  text: "Hello! Welcome to Dotclone.",
  provider: "elevenlabs",
  model: "eleven_v3",
  voice: "emma",
  settings: {
    stability: 75
  }
});

// Get the audio URL
console.log(audio.url);

// Or download
await audio.download("welcome.mp3");

// Using emotion brackets
const audio = await client.tts.generate({
  text: "[excited] Wow, this is amazing! [laughs] I love it!",
  provider: "elevenlabs",
  model: "eleven_v3",
  voice: "emma"
});

console.log(audio.url);

curl -X POST "https://api.dotclone.com/v1/tts/generate" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Hello! Welcome to Dotclone.",
    "provider": "elevenlabs",
    "model": "eleven_v3",
    "voice": "emma",
    "settings": {
      "stability": 75
    }
  }'

{
  "id": "tts_abc123",
  "url": "https://cdn.dotclone.com/audio/tts_abc123.mp3",
  "duration": 2.5,
  "format": "mp3",
  "created_at": "2025-01-15T10:30:00Z"
}

For complete API documentation, see the TTS API Reference.

Related Features

Explore more Dotclone features: