> ## Documentation Index
> Fetch the complete documentation index at: https://docs.enconvo.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Text to Speech

> Convert text to natural-sounding speech with multiple TTS providers

## Overview

EnConvo integrates with 13+ Text-to-Speech providers, giving you access to hundreds of natural-sounding voices across dozens of languages. Whether you want to listen to AI responses, read selected text aloud, or convert documents to audio files, EnConvo makes it seamless.

## Supported TTS Providers

<CardGroup cols={2}>
  <Card title="OpenAI TTS" icon="microphone">
    High-quality voices (alloy, echo, fable, onyx, nova, shimmer) with tts-1 and tts-1-hd models
  </Card>

  <Card title="ElevenLabs" icon="waveform-lines">
    Industry-leading voice synthesis with hundreds of voices and multiple models including flash v2.5
  </Card>

  <Card title="Microsoft Azure TTS" icon="windows">
    Enterprise-grade TTS with multilingual neural voices like EmmaMultilingualNeural
  </Card>

  <Card title="Edge TTS" icon="globe">
    Free Microsoft Edge voices -- no API key required
  </Card>

  <Card title="Google Cloud TTS" icon="google">
    Google's neural TTS with WaveNet and Neural2 voices
  </Card>

  <Card title="Gemini TTS" icon="sparkles">
    Google Gemini-powered TTS with style control and multi-speaker support
  </Card>

  <Card title="MiniMax TTS" icon="volume-high">
    High-quality multilingual speech with turbo and HD models
  </Card>

  <Card title="xAI TTS" icon="bolt">
    Expressive voices (Eve, Ara, Rex, Sal, Leo) with speech tag support for 20+ languages
  </Card>

  <Card title="Speechify TTS" icon="headphones">
    Simba model family -- Base, English, Multilingual, and Turbo variants
  </Card>

  <Card title="Straico TTS" icon="layer-group">
    Access ElevenLabs and OpenAI TTS through a single Straico API key
  </Card>

  <Card title="macOS System TTS" icon="apple">
    Built-in macOS `say` command -- works offline with system voices
  </Card>

  <Card title="Kokoro TTS (Local)" icon="shield-halved">
    Fully local, privacy-first TTS powered by the Kokoro model via FluidAudio
  </Card>
</CardGroup>

## Provider Comparison

| Provider            | Quality   | Speed  | Offline | Free Tier              | Languages |
| ------------------- | --------- | ------ | ------- | ---------------------- | --------- |
| **OpenAI TTS**      | Excellent | Fast   | No      | No                     | 50+       |
| **ElevenLabs**      | Excellent | Fast   | No      | Limited                | 29+       |
| **Microsoft Azure** | Excellent | Fast   | No      | Free via Enconvo Cloud | 140+      |
| **Edge TTS**        | Good      | Fast   | No      | Yes (free)             | 90+       |
| **Google Cloud**    | Excellent | Fast   | No      | No                     | 40+       |
| **Gemini TTS**      | Excellent | Medium | No      | No                     | 24+       |
| **MiniMax**         | Excellent | Fast   | No      | No                     | 17+       |
| **xAI TTS**         | Good      | Fast   | No      | No                     | 20+       |
| **Speechify**       | Good      | Fast   | No      | No                     | 20+       |
| **macOS System**    | Basic     | Fast   | Yes     | Yes (free)             | 30+       |
| **Kokoro (Local)**  | Good      | Fast   | Yes     | Yes (free)             | Multiple  |

## Getting Started

<Steps>
  <Step title="Open Settings">
    Navigate to the TTS command settings in EnConvo. You can find TTS configurations under the **TTS** extension.
  </Step>

  <Step title="Choose a TTS Provider">
    Select your preferred provider from the **TTS Provider** dropdown. Options include cloud providers (OpenAI, ElevenLabs, Azure) and free options (Edge TTS, System TTS).
  </Step>

  <Step title="Configure Credentials">
    For cloud providers, set up your API key through the Credential Provider setting. If you are on the **Enconvo Cloud Plan**, Microsoft TTS and MiniMax TTS are available without your own API key.
  </Step>

  <Step title="Select a Voice">
    Each provider offers different voices. Browse the **Voice** dropdown to find one that fits your needs. You can preview voices using the built-in preview feature.
  </Step>

  <Step title="Adjust Speed">
    Set your preferred speech speed from 0.25x to 4x using the **Speech Speed** dropdown. The default is 1.2x.
  </Step>
</Steps>

## Usage Methods

### Read Aloud

The most common way to use TTS -- have EnConvo read text aloud in real time.

1. Select any text on your screen
2. Trigger the **Read Aloud** command from the SmartBar or PopBar
3. EnConvo streams the audio as it generates, so playback starts almost immediately

You can also click the speaker icon on any AI chat response to read it aloud.

### Text to Audio File

Convert text into a saved audio file for later use.

1. Open the **TTS (Text To Speech)** command
2. Enter or paste the text you want to convert
3. The audio file is saved to your specified output directory
4. Use the **Show in Finder** or **Save As** actions to manage the file

### Gemini TTS (Style-Controlled)

Gemini TTS offers unique style-controlled speech generation.

**Single Speaker:**

```
Read aloud with a dramatic flair: It was a dark and stormy night..
```

**Multi-Speaker (dialog):**

```
Read aloud in a warm, welcoming tone
Speaker 1: Hello! We're excited to show you our native speech capabilities
Speaker 2: Where you can direct a voice, create realistic dialog, and so much more.
```

Gemini TTS supports models like **Gemini 2.5 Flash Preview TTS** and **Gemini 2.5 Pro Preview TTS**, with voice options such as Zephyr, Puck, and more.

### Convert SRT Subtitles to Audio

Convert subtitle files to audio:

1. Provide your `.srt` subtitle file
2. EnConvo processes each subtitle segment with the configured TTS provider
3. Outputs a synchronized audio file

## Voice Configuration by Provider

<Tabs>
  <Tab title="OpenAI">
    **Models:** tts-1 (fast), tts-1-hd (high quality)

    **Voices:**

    | Voice   | Character                |
    | ------- | ------------------------ |
    | alloy   | Neutral, balanced        |
    | echo    | Warm, conversational     |
    | fable   | Expressive, storytelling |
    | onyx    | Deep, authoritative      |
    | nova    | Friendly, upbeat         |
    | shimmer | Clear, gentle            |

    You can also add custom voices if available through the OpenAI API.
  </Tab>

  <Tab title="ElevenLabs">
    **Models:** eleven\_flash\_v2\_5 (recommended), and more available via API

    ElevenLabs provides hundreds of pre-made voices plus custom voice cloning. Browse voices in the dropdown or add a custom voice ID.
  </Tab>

  <Tab title="Microsoft Azure">
    **Voices:** 400+ neural voices across 140+ languages

    Default: `en-US-EmmaMultilingualNeural` -- a multilingual voice that adapts to the input language automatically.

    <Tip>
      Azure TTS is available **free** through the Enconvo Cloud Plan, with no separate API key required.
    </Tip>
  </Tab>

  <Tab title="Edge TTS">
    Microsoft Edge TTS provides high-quality neural voices for free. No API key is required. Voice list is fetched dynamically from Microsoft's Edge services.
  </Tab>

  <Tab title="xAI">
    **Voices:**

    | Voice | Style                 |
    | ----- | --------------------- |
    | Eve   | Energetic, upbeat     |
    | Ara   | Warm, friendly        |
    | Rex   | Confident, clear      |
    | Sal   | Smooth, balanced      |
    | Leo   | Authoritative, strong |

    Supports 20+ languages with automatic language detection.
  </Tab>
</Tabs>

## Speed Settings

All providers support adjustable speech speed:

| Speed              | Use Case                                |
| ------------------ | --------------------------------------- |
| **0.5x -- 0.75x**  | Careful listening, language learning    |
| **1.0x**           | Normal speaking pace                    |
| **1.2x** (default) | Slightly faster, efficient listening    |
| **1.5x -- 2.0x**   | Speed listening, familiar content       |
| **2.5x -- 4.0x**   | Scanning content, experienced listeners |

## Offline TTS Options

For privacy-first or no-internet scenarios, EnConvo offers two fully offline options:

<AccordionGroup>
  <Accordion title="macOS System TTS">
    Uses the built-in macOS `say` command. No downloads required -- works with any voice installed in System Settings > Accessibility > Spoken Content > System Voice.

    * Supports M4A output format
    * Adjustable speed
    * Works completely offline
    * Quality varies by voice; download enhanced voices for better quality
  </Accordion>

  <Accordion title="Kokoro TTS (via FluidAudio)">
    A local neural TTS model bundled with EnConvo's FluidAudio framework. Runs entirely on your Mac using Apple Silicon acceleration.

    * High-quality neural speech
    * No internet connection required
    * No API key needed
    * Your text never leaves your device
  </Accordion>
</AccordionGroup>

## Using TTS in Chat

EnConvo integrates TTS directly into the AI chat experience:

1. **Manual playback:** Click the speaker icon on any AI response to hear it read aloud
2. **Auto-TTS:** Enable automatic TTS in chat settings to have every response read aloud
3. **Playback controls:** Pause, resume, or stop playback at any time

## Using TTS with Translation

The Translate command can automatically play TTS audio of the translated result:

1. Open the **Translator** command settings
2. Enable **Automatically Play TTS Audio** under the Text-to-Speech group
3. Select your preferred TTS provider
4. Every translation result is now read aloud automatically

## Sound Effects Generation

EnConvo can also generate sound effects from text descriptions:

1. Use the **Text To Sound Effect** command
2. Describe the sound you want in English (up to 200 characters)
3. The more detailed the description, the better the result

```
A gentle rain falling on a tin roof with distant thunder
```

## Troubleshooting

<AccordionGroup>
  <Accordion title="No audio playing">
    1. Check that your Mac's audio output is working (System Settings > Sound)
    2. Verify the TTS provider is configured with valid credentials
    3. Try switching to Edge TTS or System TTS to rule out API issues
    4. Check the console logs for error messages
  </Accordion>

  <Accordion title="Voice sounds robotic or low quality">
    1. Switch to a higher-quality provider like ElevenLabs or OpenAI TTS HD
    2. If using OpenAI, switch from `tts-1` to `tts-1-hd`
    3. Adjust the speed -- very high speeds can reduce quality
    4. Try a different voice; some voices perform better than others
  </Accordion>

  <Accordion title="TTS is too slow">
    1. Use a turbo/flash model variant when available (e.g., ElevenLabs flash v2.5, MiniMax turbo)
    2. Edge TTS and System TTS are typically the fastest options
    3. Check your internet connection for cloud providers
    4. Try reducing the text length for faster initial playback
  </Accordion>

  <Accordion title="Wrong language pronunciation">
    1. For xAI TTS, explicitly set the language instead of using Auto Detect
    2. Use a multilingual voice like Azure's EmmaMultilingualNeural
    3. Ensure the text language matches the voice's supported languages
  </Accordion>
</AccordionGroup>

## Enconvo Cloud Plan

The Enconvo Cloud Plan includes built-in access to several TTS providers without needing your own API keys:

| Provider            | Via Cloud Plan |
| ------------------- | -------------- |
| Microsoft Azure TTS | Included       |
| MiniMax TTS         | Included       |
| xAI TTS             | Included       |

<Note>
  Cloud Plan TTS usage consumes your Enconvo points. Check Settings > Usage for your current balance.
</Note>

## Related Features

<CardGroup cols={2}>
  <Card title="Dictation" icon="microphone" href="/features/dictation">
    Convert speech to text
  </Card>

  <Card title="AI Chat" icon="comments" href="/ai/chat">
    Chat with AI and listen to responses
  </Card>

  <Card title="Translation" icon="language" href="/ai/translate">
    Translate and listen to results
  </Card>

  <Card title="Speech Recognition" icon="ear-listen" href="/ai/speech-recognition">
    Advanced speech-to-text providers
  </Card>
</CardGroup>