# Single Speaker Mode

Single Speaker Mode generates audio from a continuous script delivered by one voice. It is the most straightforward mode in Speech Generation — configure your voice, accent, and style, write your script, and generate.

***

#### When to Use It

Single Speaker Mode is best for any content where one voice delivers the entire audio without interruption or dialogue:

* Video and presentation voiceovers
* Podcast narration and solo episode scripts
* Product walkthrough and demo audio
* Marketing and promotional announcements
* Instructional and training content
* Audiobook-style narration

***

#### Step-by-Step Configuration

* **Step 1 — Select Single Speaker Mode** Open the Speech Generation workspace and select **Single Speaker** from the mode selector.
* **Step 2 — Choose a Voice** Browse the voice library and click any voice to preview it. Select the one that best fits your content and audience. See Voices, Accents & Style → for a full breakdown of voice categories and filtering options.
* **Step 3 — Set Language and Accent** Write your script in the language you want the audio generated in — the output language automatically matches your input text. If your language has multiple regional dialects, select the appropriate accent to improve pronunciation accuracy and naturalness.
* **Step 4 — Add Style Instructions** Enter a style instruction in the **Style Prompt** field to guide the tone and delivery of the voice. This is optional but recommended for content that requires a specific emotional register.

**Examples:**

```
Warm and conversational, like speaking to a friend.
```

```
Professional and authoritative — clear and measured delivery.
```

```
Energetic and enthusiastic, high-energy marketing tone.
```

**Step 5 — Write Your Script** Enter or paste your script into the script input field.

* Maximum length: **4,000 characters**
* Write in any language — audio is generated in that language automatically
* Use proper punctuation to control pacing and natural pauses
* Break long paragraphs into shorter sections for more natural delivery
* Add exclamation marks and question marks where tone emphasis is needed

{% hint style="info" %}
Well-punctuated scripts consistently produce more natural-sounding audio. Treat punctuation as pacing instructions — a comma creates a brief pause, a full stop creates a longer one, and an exclamation mark adds emphasis.
{% endhint %}

**Step 6 — Select a Model**

| Model         | Best For                                             |
| ------------- | ---------------------------------------------------- |
| **Flash TTS** | Draft generation, script testing, quick iterations   |
| **Pro TTS**   | Final production output, client delivery, publishing |

{% hint style="info" %}
Use Flash TTS to validate your voice, accent, style, and script before committing to Pro TTS for the final generation. This saves credits without compromising final output quality.
{% endhint %}

**Step 7 — Generate** Click **Generate**. The audio output appears below the configuration area once processing is complete.

***

#### Reviewing and Using Your Output

Once generated, you can:

* **Play** the audio to review it
* **Download** the file to your device
* **Share** via a shareable link
* **Regenerate** by adjusting your script, style, or model if the output needs refinement

All generated audio is automatically saved to the **Audio History panel** and to **Dashboard → History** for future access. See Managing Generated Audio → for full details.

***

#### Resetting

The **Reset** option clears all current configuration — voice, accent, style instructions, script, and model selection. Use this when starting a completely new generation to avoid carrying over previous settings.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.qolaba.ai/speech-generation/speech-generation-modes/single-speaker-mode.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.