Bo (@BoBowchan) profile picture
Redwood City, California
Joined May 2015
Photo by Bo (@BoBowchan)Photo by Bo (@BoBowchan)
Delta neutral talk on YouTube (no annoying bar at the bottom) #ETHDenver youtu.be/bL87uHDygbQ
1
2
7
How do you run a real-time voice agent on a slower, but more capable model without making callers wait? EliseAI engineer @bobowchan draws on his experience building self-driving cars to explain how we got voice agents listening, thinking and speaking in parallel, without trading intelligence for speed. Watch the full talk ↓ hubs.la/Q04y9Ldb0
4
1
1
7
1,289
Live now: our Voice Track from AI Engineer World's Fair 2026. Half a second that made a product feel slow, a trillion phone calls a year, and the case for agents that know when not to speak. Thesis: voice agents do not fail at talking. They fail at listening. youtube.com/watch?v=LZuWZRze… - The New Primitives: @kwindla, Daily - Speech-to-Speech Model Research at Google DeepMind: @valeriawu_ & Tom Ouyang - Voice Agents Can Just Do Things: @charlierguo, OpenAI - Your Voice Agent is Just a Walkie Talkie: @neilzegh, Gradium - Voice-First AI Companion: @paularambles, Tolan - 5 Voice Agent Failure Modes You'll Hit in Week One: @bevenky, Plivo - I Monitored Crime Audio. Voice Agents Scare Me More. @sumanyu, Hamming AI - Realtime Voice Agents with Frontier Intelligence: @bobowchan, EliseAI - "My name is... my name is...": Midam Kim, ServiceNow - Act, Confirm, or Stop? Amit Desai, Roku
8
4
1
17
3,293
excited to finally share this. for the past couple months @elise_ai has been an early access partner with @OpenAIDevs on gpt-live-1. we've brought it into production starting with healthcare. when patients call, they're usually trying to book an appointment or sort out a billing question. a bad call means they just don't get help. full-duplex, handles interruptions, stays engaged mid-task. cascaded pipelines can't do this. patients get what they called for. it's been great collab-ing with you @theteriyu @pbbakkum @SaiMandhan and the rest of the openai team! shout out to the entire voiceAI team including @BoBowchan @TheRealAk914!
GPT-Live-1 is now available in the API. Bring ChatGPT’s natural back-and-forth to your app, with voice agents that listen while they speak and work with the models and harness you choose.
2
4
1
12
1,961
Been hard to keep this one a secret! For the past couple of months, @elise_ai has been working with @OpenAIDevs as an early design partner for GPT‑Live-1. I still remember my excitement back in 2024 when the first S2S models came out, but it took a long time to get to production - now it feels like we’re finally there. There are lots of really interesting improvements to using GPT-Live-1 – some less obvious than others:
11
10
5
89
15,584
Works in codex though :)
why can’t cursor or claude allow you to listen to audio files? kinda annoying right
1
162
Last week at @aiDotEngineer World Fair, staff software engineer Bohan Li broke down @elise_ai's cascaded voice agent harness and shared the unorthodox tricks we do to unlock frontier capability at real-time speeds. We drew inspiration from the self-driving car stack, which orchestrates models across perception, planning and controls to deliver a system capable of making complex decisions in milliseconds.
1
6
1
17
2,596
Extremely proud of the team @cartesia for launching Sonic 3.5, which sets a new state of the art for TTS I personally led the technical direction of this model; we built it ground up from first principles, and it contains multiple non-trivial ideas that differ substantially from anything we’ve seen in the literature. It’s been very gratifying to see research bets play out and the strong research team at Cartesia continue to grow!
Cartesia’s Sonic-3.5 takes the #1 spot on the Artificial Analysis Speech Arena Leaderboard, surpassing Inworld Realtime TTS 1.5 Max and Google’s Gemini 3.1 Flash TTS Sonic-3.5 is the latest TTS model from @cartesia . It supports 42 languages, including 9 Indian languages, with 500+ voices available out of the box. The model has been highly preferred among voters in the TTS Arena, with its demonstrated naturalness and accurate transcript following. Key takeaways: ➤ Quality: Sonic-3.5 has an Elo score of 1,218 (+16/-16) based on 1,144 arena appearances, placing it ahead of Inworld Realtime TTS 1.5 Max at 1,194 and Gemini 3.1 Flash TTS at 1,209 ➤ Pricing: Sonic-3.5 is priced at $39/1M characters, a premium compared to Gemini 3.1 Flash TTS at $18.3/1M characters, and Inworld Realtime TTS 1.5 Max at $35/1M characters ➤ Speed: 105.5 characters per second, compared to 205 characters per second for Inworld Realtime TTS 1.5 Max and 26.3 characters per second for Gemini 3.1 Flash TTS See more details and listen to samples below 🧵
6
19
188
21,257
Really proud to announce Sonic-3! Sonic-2 gave us speed and accuracy and Sonic-3 adds emotion and naturalness on top. This makes it the best TTS model in the world. But don't just take my word for it, try it out yourself! cartesia.ai/sonic
13
434
1,398
1,215
395
8,389
4,880,911
We've raised a $64M Series A led by @kleinerperkins to build the platform for real-time voice AI. We'll use this funding to expand our team, and to build the next generation of models, infrastructure, and products for voice, starting with Sonic 2.0, available today. Link below to try it free 👇
110
105
69
1,058
329,443
We've raised $27M from Index Ventures, Lightspeed, Factory, Conviction, SVA, General Catalyst, A* and our wonderful angels. Cartesia's audio models power the next generation of voice agents, digital media, and assistants across startups and large enterprises. Our mission is to build real-time intelligence with long memory, that runs wherever you are. Multimodal brains for everyone!
34
53
40
401
230,950
Today, we’re unveiling a significant milestone in our journey toward ubiquitous artificial intelligence: AI On-Device. Our team pioneered a radically more efficient architecture for AI with state space models (SSMs). Now, we’ve optimized and deployed them at the edge. We believe the future of AI runs on your device, where it can process continuously and is reliable, private, and secure. Read our full blog post here: cartesia.ai/blog/on-device
11
79
27
355
108,773
This is proof of my account ownership and participation in @0xPalladium. ▫️▫️▫️▫️▫️▫️▫️▫️▫️ f45f7e67dbf3ed82ba322fcd9bf1abdaa3ef8e43c58cda50742da060723693d8
2
if you're in SF or will be in SF this summer, engage with this tweet & i'll reply/dm you with some early access to all things IRL/events 👀
821
52
5
2,688
Link to my talk on Advanced Delta Neutral strategies #ETHDenver twitch.tv twitch.tv/videos/1303251909?…
3