Understanding the Sidekick Voice

The term "Sidekick" refers to a tone that conveys enthusiasm, support, and liveliness - but also, in a classic sense: loyalty. This typically includes a lively pace, energetic intonation, and cheerful inflections to deliver a spirited and engaging performance.

The Sidekicks's Voice - First, REGISTER at ElevenLabs! Once you're a registered user, you can upload the SIDEKICK'S VOICE* to your "My Voices" directory and start using it right away for your text-to-speech project.

Here's the classic idea of a sidekick, interpreted by JESPER

How to Create a Sidekick TTS Voice

To create a TTS output that sounds 'Sidekick', you'll need to adjust the stability and similarity sliders to produce an enthusiastic and supportive tone. Here’s how you might modify your routine:

• Stability Slider: Set the stability slider to a moderate value, around 60-70. This ensures a consistent and lively delivery.
• Similarity Slider: Set the similarity slider to a higher value, around 70-80. This ensures consistent energetic and supportive inflections.

Using the Exaggeration Slider

The exaggeration slider in ElevenLabs TTS can be useful when trying to achieve a specific tone such as 'Sidekick'. It allows you to amplify the expressiveness of the generated voice, making the enthusiasm more pronounced.

How the Exaggeration Slider Works

Exaggeration Slider: This slider adjusts the intensity of the expressiveness in the voice. At higher values, the supportive cues in the speech are more pronounced, making the output sound more enthusiastic and lively.

For a Sidekick Tone

To make the voice sound more like a sidekick, you can set the exaggeration slider to a higher value. This will enhance the energetic and supportive characteristics, making the voice sound more enthusiastic and engaging.

Example Routine

• Stability Slider: Set to 60-70. This ensures a consistent and lively delivery.
• Similarity Slider: Set to 70-80. This ensures consistent energetic and supportive inflections.
• Exaggeration Slider: Set to a higher value, around 70-80. This amplifies the expressiveness, making the voice sound more enthusiastic and engaging.

Advanced Techniques for a Sidekick Voice

Optimizing your 'Sidekick' voice involves several techniques to ensure the AI captures the enthusiasm and supportiveness you aim for. Here are some strategies:

1. Punctuation Marks

• Periods (.): Use periods to indicate full stops and help the AI understand when to pause briefly, creating a lively and clear rhythm.
• Commas (,): Use commas to indicate shorter pauses, which can help convey brief breaks in thought or emphasis.
• Exclamation Marks (!): Use exclamation marks to indicate excitement, enthusiasm, or strong support.

2. Capital Letters

• Emphasis: CAPITALIZE words that need emphasis or are important for the tone of the message.

3. Text Formatting and Structure

• Short Sentences: Use shorter sentences for clarity and to convey a more dynamic or enthusiastic tone.
• Paragraph Breaks: Use paragraph breaks to indicate a change in thought or topic, which can help create a more natural speech flow.

4. Emotional Cues and Stage Directions

• Emotional Annotations: Include annotations like [enthusiastically], [supportively], [cheerfully], or [excitedly] to specify the intended emotion or tone.
• Stage Directions: Include brief stage directions to suggest how something should be said.

5. Contextual Clarity

• Descriptive Context: Add descriptions or context before dialogue to set the scene.
• Consistent Tone: Maintain a consistent tone throughout the script to help the AI understand the overall emotional arc.

6. Testing and Iteration

• Listen and Adjust: Generate the speech, listen carefully, and adjust the text as needed to achieve the desired emotional effect.
• Experiment: Try different combinations of punctuation, capitalization, and annotations to see what works best for your specific use case.

Example Script with Optimizations

Here is an example script that incorporates these techniques: