Can you tell the current voice model what feelings and tone it should communicate with? If not it isn't even comparable, being able to control how it reads things is absolutely revolutionary, that is what was missing from using these AI models as voice actors.
No you can't, at least not directly - you can influence the tone it uses a little through the content you ask it to read.
Being able to specifically request different tones is a new and very interesting feature.
+1. Check the demo video in OP titled "Sarcasm". Human asks GPTo to speak "dripping in sarcasm". The tone that comes back is spot on. Comparing that against current voice model is a total sea change.
The voice mode was quite good but the latency and start / stop has been encumbering.
Re:GPT-4o
by duckmysick on Monday May 13, 2024 @05:08PM
(#40348449)
Slight off-topic, but I noticed you've updated your llm CLI app to work with the 4o model (plus bunch of other APIs through plugins). Kudos for working extremely fast. I'm really grateful for your tool; I tried many others, but for some reason none clicked as much as your.
Link in case other readers are curious: https://llm.datasette.io
The new voice mode sounds better, but the current voice mode did also have inflection that made it feel much more natural than most computer voices I've heard before.