Concept:

• Sam’s bearded dragon, Little Brother, has been scratching at the glass of his enclosure. His family are worried about LB because they aren’t sure of what is causing his stress.
• We are wanting to make an action packed short film that follows the adventure of a runaway bearded dragon. LB is experiencing a range of teen emotions and is in search to find some like-minded creatures.
• LB does not speak because this is a real action film, but we want to experiment with AI tools to create a “voice” that will play as his inner monologue 

Prompt:

• Write a synopsis for a short film about a bearded dragon that is experiencing puberty and a rollercoaster of emotions. Ultimately he wants to find other dragons that he can relate with, but to do that, he needs to escape from his owner’s home. The family love him so much and go on a big hunt to find him. The hunt lasts for 4 days and they get very close to finding him, however something always gets in the way

GPT Synopsis:

‘Meet LB, a bearded dragon undergoing puberty, which triggers a wild ride of emotions. Yearning for connection with his own kind, LB plots an escape from his loving family. His goal: to find fellow dragons who understand him.

LB’s family soon notices his absence and launches a four-day search, filled with comical mishaps. Despite being close to finding LB, fate continually intervenes. Meanwhile, LB faces challenges and discovers unexpected allies in the outside world.

As the family and LB’s paths converge, LB learns that his longing for connection is mirrored by his family’s love. The tale explores adolescence, family bonds, and self-discovery, reminding us that true connections might be closer than we think.’

Score:

Chosen Artowork:

https://www.youtube.com/watch?v=sc9OjL6Mjqo

“For the past two years, we have been building an ensemble in Berlin.

One member is a nascent machine intelligence we have named Spawn. She is being raised by listening to and learning from her parents, and those people close to us who come through our home or participate at our performances.

Spawn can already do quite a few wonderful things. ‘Godmother’ was generated from her listening to the artworks of her godmother Jlin, and attempting to reimagine them in her mother’s voice.

This piece of music was generated from silence with no samples, edits, or overdubs, and trained with the guidance of Spawn’s godfather Jules LaPlace.”

I chose this artwork because it had a huge sound element to it and i felt it was inspiring due to our focus for the week being around sound design.

Embarking on a journey through Eleven Labs to explore AI voice generation was a fascinating experience that resonated with Simon Willison’s insights in his “Catching up on the weird world of LLMs” talk at North Bay Python 2023. Just as he highlighted the diverse and quirky behaviour of LLMs, our class dove into the intriguing realm of AI-generated voices. I first played around with the Blip outers script but I thought it would be interesting to feed the AI some of my favourite childhood Dr Seuss stories.  

Our interactions with Eleven Labs revealed a spectrum of responses. Sometimes the text couldn’t be properly spoken or sounded erratic depending on the settings we plugged into it, I liked to play around with accents and long words to see how it would interpret.

Eleven labs was only part of what we did in this class, we also looked at recording our natural voices on our phones, reading the script we created earlier on ChatGPT, we then put this recording into Reduct and got it to transcribe the recording. This process was funny. My group played around with making the script as natural as possible and as a result we found ourselves doing a lot of improvisation. 

(ChatGPT Version)

Embarking on an odyssey through Eleven Labs to delve into the realm of AI voice generation proved to be a profoundly captivating experience that harmoniously echoed the insights shared by Simon Willison during his discourse, “Catching up on the weird world of LLMs,” at the distinguished North Bay Python event in 2023. Much like Willison’s elucidation of the nuanced and idiosyncratic behaviors of Large Language Models (LLMs), our academic cohort wholeheartedly embraced the enigmatic domain of AI-generated vocalizations.

Initially, I engaged with the Blip outers script, but the allure of further experimentation beckoned, prompting me to imbue the AI with cherished childhood tales by Dr. Seuss—an endeavor that promised a distinctive creative encounter.

Within the framework of Eleven Labs, our engagements unveiled an expansive spectrum of responses. Occasional phonetic dissonance and fluctuating coherency arose, influenced by the intricate amalgamation of parameters we invoked. Intriguingly, my fascination propelled me to manipulate accents and lexicon complexity, thereby unraveling the AI’s intricate interpretation process.

The Eleven Labs dimension, while pivotal, merely constituted a segment of our pedagogical voyage. We ventured further by capturing our organic vocal cadences through mobile devices, reciting scripts authored earlier via ChatGPT. Subsequently, immersing the recordings within Reduct’s purview, we navigated the whimsical tapestry of transcriptions—an endeavor that induced hearty amusement.

Particularly within my collaborative group, an affinity for authenticity galvanized us to cultivate a narrative that mirrored natural discourse. This pursuit not only engendered spontaneous improvisations but also kindled a mosaic of comical moments, rendering the learning process both insightful and enjoyable.

Week 4 Sketch

Blog 3:

https://www.mediafactory.org.au/grace-rosebirch/2023/08/06/blog-post-3-automatic-for-the-people/

Blog 2:

https://www.mediafactory.org.au/grace-rosebirch/2023/08/03/blog-post-2-automatic-for-the-people/

Blog 1:

https://www.mediafactory.org.au/grace-rosebirch/2023/07/25/blog-post-1-automatic-for-the-people/

 Outers (as a kids cartoon)

Blog 3 Reflection:

For my final blog post I was really trying to dive deeper into the experimental ways we can use chatGPT. My group definitely had fun with pushing the boundaries and just throwing as many random ideas out there and generating it to see what came out of these ideas. Some of the scenes that came out of this trial were more realistic to what a scene in a TV show or movie would be like, others were more generic and cringe. When this happens you can refer back to the weekly reading and understand and think about the comparison between ChatGPT and a blurry JPEG. “It retains much of the information on the Web, in the same way that a jpeg retains much of the information of a higher-resolution image, but, if you’re looking for an exact sequence of bits, you won’t find it; all you will ever get is an approximation.” This approximation can be understood as the reasoning behind it being very unhumanistic with the dialogue and some of the scenes. An example of a way we tried it was giving it emotive words on certain lines and seeing if that changed the dialogue that came out. Eventually when we put in our final prompt asking for it to be like a nickelodeon kids tv show, it became a lot more believable due to the number of other prompts prior we filtered our way down to our final result. However this final scene is still not perfect to the human eye and definitely would need to be slightly changed to make it more true to the genre and also just be enjoyable to watch. 

Bibliography:

Chiang, T. (2023) CHATGPT is a blurry JPEG of the web, The New Yorker. Available at: https://www.newyorker.com/tech/annals-of-technology/chatgpt-is-a-blurry-jpeg-of-the-web (Accessed: 06 August 2023). 

Nickelodeon Australia (no date) Nickelodeon. Available at: https://www.nick.com.au/ (Accessed: 06 August 2023).

The Outers

\