# Text to speech

- Human page: https://happytails.ai/en/speech-tools/text-to-speech/
- Markdown: https://happytails.ai/en/speech-tools/text-to-speech.md
- Structured JSON: https://happytails.ai/agents/en/speech-tools/text-to-speech/index.json
- Visibility: public

## Tool capabilities

| Property | Value |
| --- | --- |
| Tool ID | `text-to-speech` |
| Category | speech-tools |
| Implementation | Registered implementation. Registration alone is not a production-quality guarantee. |
| Browser execution | Use the visible action or interactive controls. |
| Browser processing | Browser; see tool notes for network behavior. |
| HTTP API | Not callable through HTTP. |
| Browser-agent interface | No callable WebMCP interface. |

### Implementation notes

Uses voices supplied by your browser or operating system. Some voices may use the provider’s network service. Playback only; audio-file export is not supported.

### Inputs and settings

No free-text input is required. Use the file inputs and/or settings below.

No additional settings are declared for this tool.

### Planning specification

Generate downloadable WAV from text using stock voices; choose language and speed; preview short passages; handle punctuation and long-text chunking. Text-to-voice and voiceover are aliases or modes.

This describes intended requirements. Use the implementation notes, interface schema and observed output to determine current support.

### Complete machine-readable capability record

```json
{
  "id": "text-to-speech",
  "category": "speech-tools",
  "built": true,
  "requirements": "Generate downloadable WAV from text using stock voices; choose language and speed; preview short passages; handle punctuation and long-text chunking. Text-to-voice and voiceover are aliases or modes.",
  "implementation": {
    "fields": [],
    "input": false,
    "note": "Uses voices supplied by your browser or operating system. Some voices may use the provider’s network service. Playback only; audio-file export is not supported.",
    "experience": {
      "automatic": false,
      "single": false,
      "label": "Your text",
      "placeholder": "Type or paste your input…",
      "help": "Up to 1,000,000 characters. Review the settings before running.",
      "action": null
    },
    "mode": "explicit",
    "interactive": true
  },
  "execution": "Browser interface",
  "api": null,
  "browser_agent": {
    "supported": false,
    "name": null,
    "discovery": "WebMCP on the human page in a supporting browser",
    "verification": "See audit/API-AUDIT.md; availability is not verification"
  }
}
```

## Page guide

Read text aloud with a browser voice.

## Useful next steps

- [Voiceover timing](https://happytails.ai/en/speech-tools/voiceover-timing/): Estimate the speaking pace needed for a target duration. ([Markdown](https://happytails.ai/en/speech-tools/voiceover-timing.md))

- [PDF to audio](https://happytails.ai/en/speech-tools/pdf-to-audio/): Read selectable PDF text aloud using a local system voice. ([Markdown](https://happytails.ai/en/speech-tools/pdf-to-audio.md))

- [Read aloud](https://happytails.ai/en/speech-tools/read-aloud/): Listen to written text with a browser voice. ([Markdown](https://happytails.ai/en/speech-tools/read-aloud.md))

## How to use Text to speech

1. Enter the text you want to hear.
2. Choose a voice and speaking rate, then choose Speak.
3. Choose Stop to end playback.

## What to expect

Read text aloud with a browser voice. Choose an available voice and a speaking rate from 0.1 to 3. Some voices may use their provider’s network service. This tool plays speech; it does not export an audio file.