🎙️ Brand Voice Generator: User Manual & Guide

Introduction

Welcome to the Brand Voice Generator, an internal tool designed to transform your written scripts into high-quality, AI-generated voice-overs instantly. Whether you are creating podcast intros, social media narration, or internal training videos, this tool allows you to produce consistent, brand-aligned audio without needing a recording studio.

1. Getting Started

Before you begin, ensure you are logged into the WordPress dashboard.

• Permissions: This tool is restricted to specific user roles. If you cannot see the interface, please contact the site administrator.

2. The Interface: Key Controls

The interface is divided into four logical sections:

1. Voice Selection: Choosing the “actor” for your script.

2. Script Input: Where your text goes.

3. Fine-Tuning Controls: Sliders and Toggles for customization.

4. Action Area: Generating, listening, and downloading.

3. Step-by-Step Usage Guide

Step 1: Select Your Voice Personality

Choose the voice that best fits the emotion of your content from the dropdown menu.

• Kore (Clear, Firm): Best for corporate announcements, tutorials, and instructional content where clarity is king.

• Puck (Upbeat, Enthusiastic): Ideal for marketing promos, social media reels, and exciting announcements.

• Charon (Informative, Deep): Perfect for serious documentaries, news reading, or dramatic narration.

• Leda (Youthful, Soft): Great for storytelling, wellness content, or approachable customer service messages.

• Zephyr (Bright, Engaging): A balanced voice for vlogs, newsletters, and general engagement.

• Fenrir (Excitable, Dynamic): Use this for high-energy calls to action or gaming content.

Step 2: Enter Your Script

Type or paste your script into the Script Text box.

• Limit: The AI can handle long scripts, but for the best results, we recommend processing content in chunks of 3–5 paragraphs at a time.

Step 3: Fine-Tune the Audio

This is where you customize the delivery using the new sliders.

🎚️ Speed Slider (Rate)

Controls how fast the AI speaks.

• Default (1.0x): Natural conversational speed.

• Slower (0.8x – 0.9x): Use for complex technical explanations or dramatic storytelling.

• Faster (1.1x – 1.2x): Use for disclaimers, upbeat social media clips, or time-constrained ads.

🎚️ Pitch Slider

Controls the tone/frequency of the voice.

• Default (0): The voice actor’s natural pitch.

• Lower (Negative values): Makes the voice sound deeper and more authoritative.

• Higher (Positive values): Makes the voice sound lighter and younger.

4. Advanced Feature: SSML (Speech Synthesis Markup Language)

The SSML Toggle gives you granular control over how the script is read.

To use this feature:

1. Check the box labeled “Enable SSML”.

2. You must now use specific tags in your text box to direct the AI.

Common SSML Tags & Examples

A. Adding Pauses (<break>)

Without SSML, the AI pauses naturally at commas and periods. Use the break tag to force a longer silence for dramatic effect or to separate distinct topics.

Example Script:

Welcome to our new product launch. <break time="1s"/>
Wait until you see what we have in store. <break time="500ms"/>
It is truly revolutionary.

• 500ms = Half a second pause.

• 1s = One second pause.

B. Paragraphs and Sentences (<p> and <s>)

To ensure the AI understands exactly where a thought ends, you can wrap text in paragraph tags.

Example Script:

<p>Here is the news for today.</p>
<p>In sports, the local team won the championship.</p>

⚠️ Important: If the SSML toggle is ON, you must ensure your tags are formatted correctly. If you leave a tag unclosed (e.g., typing <speak> without </speak>), the generation may fail.

5. Generating and Downloading

1. Click “Generate Voice & Play”:

   • The button will pulse, and a loading indicator (“Synthesizing audio…”) will appear.

   • Note: Generation time depends on the length of your script. A 30-second script usually takes 3-5 seconds to generate.

2. Preview the Audio:

   • Once complete, the built-in audio player will appear and automatically start playing your clip. You can pause, scrub, and replay it immediately.

3. Download the File:

   • A green “Download WAV” button will appear next to the player.

   • Click this to save the file to your computer.

   • File Format: The file is saved as a high-quality .wav file, which is lossless and perfect for editing in Adobe Premiere, Audacity, or Davinci Resolve.

6. Troubleshooting & Pro-Tips

• “I clicked Generate but nothing happened.” Check your internet connection. If the issue persists, the API Key set by the administrator may be invalid or have exceeded its quota.

• “The voice sounds robotic.” Try adjusting the Pitch slider back to 0 and the Speed to 1.0. Extreme values (e.g., Pitch +20) can degrade the natural quality of the voice.

• “SSML isn’t working.” Ensure the Enable SSML checkbox is ticked. Double-check your tags; a typo like <braek> instead of <break> will cause the AI to read the word “break” out loud or fail entirely.

• Best Practice for Long Content: Don’t generate a 10-minute video narration in one go. Generate it paragraph by paragraph. This gives you more control over the pacing of each section and makes editing easier later.