> For the complete documentation index, see [llms.txt](https://docs.qolaba.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.qolaba.ai/chatbot/toolkit/text-to-speech.md).

# Text to Speech

The Text-to-Speech tool converts written text into natural-sounding audio directly within the chat — powered by **Gemini**. Turn any AI-generated response into a playable audio clip without leaving the conversation.

***

#### How to Use It

No toggle required. Simply prompt the chatbot to generate speech from any text in the conversation — including AI-generated responses.

**Example prompts:**

```
Generate speech for the above response.
```

```
Turn this into audio.
```

```
Read the previous paragraph in a calm, female voice.
```

```
Generate audio for this in a deep male voice with a formal tone.
```

The chatbot instantly converts the text into an audio file that plays directly within the chat interface. All generated audio clips are automatically saved to **Dashboard → History** and remain accessible in your chatbot history as well.

***

#### Voice & Style Options

**Voice library** — Choose from over 30 unique voices to match your content and audience.

**Style instructions** — Specify tone, mood, and delivery directly in your prompt. Examples: formal, excited, storytelling, conversational, calm, authoritative.

**Multi-speaker generation** — If the text contains a dialogue or conversation between two or more people, prompt the chatbot to generate a realistic multi-speaker audio clip with distinct voices for each speaker.

**Example multi-speaker prompt:**

```
Generate a multi-speaker audio clip for this dialogue —
use a professional male voice for the interviewer
and a confident female voice for the interviewee.
```

{% hint style="info" %}
For standalone audio generation outside the chatbot — including model selection, the full voice library, and style controls — see [Text-to-Speech → ](/speech-generation/voices-accents-and-style.md)
{% endhint %}