OpenAI Realtime API
product on 7 shows · 4 statements across 2 episodes · said 35 times in 10 episodes since 2024
Latent Space 19 
BG2 Pod 7 
A Product Market Fit Show 3 
Lenny's Podcast 2 
TBPN 2 
the Y Combinator Startup Podcast 1 
20VC 1
Mentions by year, every show
tap a year for its mentions
Latent Space 19BG2 Pod 7A Product Market Fit Show 3Lenny's Podcast 2TBPN 220VC 1the Y Combinator Startup Podcast 1
2026 1 mention in 1 episode
2025 17 mentions in 5 episodes 3 per episode
- Inside OpenAI Enterprise: Forward Deployed Engineering, GPT-5, and More | BG2 Guest Interview · Bg2 Pod
- Personalized AI Language Education — with Andrew Hsu, Speak
- His AI Voice Startup grew to $10M ARR in 1 Year—after 3 Years Stuck at $500K | Jordan Dearsley, F... · PMF Show
- Building the World’s Smallest Fusion Reactor | Robin Langtry on TBPN
- Why Hallucination Is Good For AI Voice Agents | Russell D'Sa on TBPN
- every mention in 2025, scene by scene →
2024 17 mentions in 4 episodes 4 per episode
- Building AGI in Real Time (OpenAI Dev Day 2024)
- Becoming an AI PM | Aman Khan (Arize AI, ex-Spotify, Apple, Cruise)
- Sam Altman: What Startups Will be Steamrolled by OpenAI & Where is Opportunity | E1223 · 20VC with Harry Stebbings
- The 10 Trillion Parameter AI Model With 300 IQ · Y Combinator
- every mention in 2024, scene by scene →
every mention on every show, scene by scene, with the transcript →
4 statements about OpenAI Realtime API, every show
Speak has no OpenAI Realtime API features in production due to cost
“We are, In the process of building a variety of experiences on top of the real-time API, I want to clarify that actually nothing is in production yet, mostly for price reasons, frankly.”
Hsu: Realtime API pricing fits customer support displacement, not consumer apps
“The pricing model of the real-time API makes more sense for something like a customer support agent, where you're very directly replacing somebody that you would pay hourly otherwise, and that's how you're seeing the pricing model for a lot of these initial ag…”
Hsu: Standard semantic VAD fails completely for language learners
“You can use like the semantic VAD on real time API for regular English conversation. And that will basically classify at every token, how likely it is that you're done speaking as a sort of normal conversational English speaker. Like in this conversation, that…”
Biggio: Forcing function calls over voice yields reliable UI control
“Speech to text is really interesting because you can prevent, you can prevent responses like audio responses and force function calls. And so you can do stuff like UI control that is like super, super reliable... If you like cut out the audio outputs and make …”