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

# Text-to-Speech

> Convert text into natural-sounding speech using preset or cloned voices.

Text-to-speech converts written text into spoken audio. You provide the text and optionally choose a voice. The agent generates an MP3 file you can play and download.

## How to generate speech

<Steps>
  <Step title="Describe what you need">
    Tell the agent what text to convert. You can type the text directly or ask the agent to write it first.
  </Step>

  <Step title="Choose a voice (optional)">
    If you do not specify a voice, the agent uses Rachel (the default). To use a different voice, mention it in your prompt.

    | Voice                | Description                    |
    | -------------------- | ------------------------------ |
    | **Rachel** (default) | Neutral, clear, conversational |
    | **George**           | Male, warm tone                |
    | **Sarah**            | Female, professional           |
    | **Charlie**          | Male, casual                   |
    | **Lily**             | Female, friendly               |
    | **Chris**            | Male, energetic                |

    You can also use a cloned voice by its ID. See [Voice Cloning](/voice-cloning).
  </Step>

  <Step title="Review and download">
    The audio file appears in the chat with a waveform player. Click play to preview, then click **Download** to save the MP3 to your device.
  </Step>
</Steps>

## Example prompts

<Prompt description="Phone greeting for a small accounting firm">
  Generate a text-to-speech voiceover using the voice "George" for our accounting firm's phone system. The script is: "Thank you for calling Oakridge Accounting. Our office hours are Monday through Friday, 9 AM to 5 PM Eastern. For tax preparation, press 1. For bookkeeping and payroll, press 2. For new client inquiries, press 3. To leave a message, press 4. Or stay on the line and someone will be with you shortly." Professional tone, medium pace.
</Prompt>

<Prompt description="Voiceover for a bakery's Instagram Reel">
  Generate a voiceover using the voice "Lily" for our bakery's Instagram Reel. The script is: "Every morning at 5 AM, we start with flour, water, salt, and our 3-year-old sourdough starter. Forty-eight hours later, you get this. Fresh from our oven to your table. Flour & Fold, Brooklyn." Warm, inviting tone, slightly slow pace to match the video.
</Prompt>

<Prompt description="Explainer narration for a fitness studio's website">
  Generate a voiceover using the voice "Chris" for our website homepage video. The script is: "CoreFit Studio is Austin's boutique fitness experience. Small group classes, personal training, and a community that actually shows up for each other. HIIT, yoga, spin, and strength. Your first class is free." Energetic but not over the top, clear pronunciation.
</Prompt>

## What you cannot do

* You cannot control speed, pitch, or emphasis. The voice model determines pacing naturally.
* You cannot add pauses or breaks at specific positions in the text.
* You cannot output in formats other than MP3 or WAV.
* You cannot mix speech with background music in one step. Generate them separately.

## Next steps

<CardGroup cols={2}>
  <Card title="Multi-Speaker Dialogue" icon="comments" href="/multi-speaker-dialogue">
    Generate conversations between multiple speakers.
  </Card>

  <Card title="Voice Cloning" icon="clone" href="/voice-cloning">
    Clone a voice from audio samples to use for speech generation.
  </Card>
</CardGroup>