Example
From Text to Feeling
It may take some time to produce a strong narration that meets the criteria for this challenge. You might go through dozens of audio generations before finding the right tone, emotion, and feeling behind the spoken words.
In Storyline, we can effectively use ElevenLabs, along with SSML tags, to adjust pauses, tone, pacing, and more. But it does take time, and often requires a lot of tweaking and fine-tuning to achieve the perfect voice setting.
In this challenge, I experimented with the new ElevenLabs V3, which was announced not long ago. Although it's still in beta, it already does a pretty decent job. Eleven V3 introduces emotional control through audio tags. You can direct voices to laugh, whisper, sing, act sarcastic, or express curiosity, among many other styles. You can also control the speed using specific tags. The most important factor in Eleven V3 is the voice you choose. It needs to be close enough to the intended delivery style. For example, if the voice is naturally loud or intense, using a tag like [whispering] may not produce good results.
My example is a short experiment using ElevenLabs V3. The audio clips were generated on their platform and then imported into Storyline. I truly hope that once this version is fully tested and stable, it will be integrated into Storyline directly. That would be an incredible experience, and a real joy allowing us to produce more emotionally rich and expressive narration than ever before.
Getting Started with the E-Learning Challenges
Find practical answers to common questions about the E-Learning Challenges, a weekly event that helps you build skills, create your portfolio, and grow as an e-learning professional.