video1.0<iframe src="https://www.loom.com/embed/8d8a03b0ec9841db856c3913d0620ae3" frameborder="0" width="1920" height="1440" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>14401920Loomhttps://www.loom.com14401920https://cdn.loom.com/sessions/thumbnails/8d8a03b0ec9841db856c3913d0620ae3-84e18ba6b871f713.gif212.4876In this video, I conducted a quick test comparing the March and December snapshots of the OpenAI text-to-speech model, focusing on how well it follows different instructions. I tested various styles, including high-pitch, low-pitch, whispering, and aggressive accents, and found that both versions performed similarly. Despite trying different voices, I couldn't notice any significant differences in the December snapshot when using the instructions parameter. I would appreciate any feedback on this, as I'm unsure if I'm missing something or if there's a different approach I should take. Cheers!