Zack Hodari

Researcher @Sesame working on Conversational Companions

[Stammy @Stammy]

@sesame We're also building beautiful, intelligent eyewear. Coming 2027.

[Stammy @Stammy]

Today we're announcing our @sesame iOS app preview, giving you a first look at our collection of personal agents, a new way to explore your curiosity and think out loud.

We’ve come a long way since the Research Preview from last year: new features, new characters, and better capabilities.

https://t.co/g6VCc1CGFB
https://t.co/M5RWoUiyP2

[Sesame @sesame]

A collection of personal agents, crafted for everyday conversation.

Preview available now on iOS.

https://t.co/Hq5ZXAqPvX

[Sequoia Capital @sequoia]

Voice is the next great interface shift.

We're partnering with @brendaniribe, @natemitchell, @_apkumar, @2rhb & the @Sesame team to bring computers to life, not just as tools, but as thought partners.

[Sesame @sesame]

We're just getting started: https://t.co/nlmmbzfdf4

[Unsloth AI @UnslothAI]

You can now fine-tune TTS models with Unsloth!

Train, run and save models like Sesame-CSM and OpenAI's Whisper locally with our free notebooks.

Unsloth makes TTS training 1.5x faster with 50% less VRAM.

GitHub: https://t.co/2kXqhhvLsb
Docs & Notebooks: https://t.co/apZrxiKs0j

[Vaibhav (VB) Srivastav @reach_vb]

HOLY SHITT, Sesame Labs just dropped CSM (Conversational Speech Model) - Apache 2.0 licensed! 💥

> Trained on 1 MILLION hours of data 🤯
> Contextually aware, emotionally intelligent speech
> Voice cloning & watermarking
> Ultra fast, real-time synthesis
> Based on llama architecture & Mimi like decoder
> Apache 2.0 licensed
> Weights on the Hub

So cool to see such a strong Speech backbone out in the wild! Kudos @sesame team! 🤗

[Zack Hodari @zhodari]

Sesame's CSM 1B base model is open-source!!! 🎉

Try it on Hugging Face https://t.co/I9WOSToF1C

💻 Code: https://t.co/2N0ddeL6pa
💾 Checkpoint: https://t.co/z8tjNXw7ca
📜 License: Apache-2.0

📚 Read our technical post and try our fine-tuned model: https://t.co/dHxlXvaNOg

[Martin Shkreli @MartinShkreli]

a half-hour episode of me acting with @sesame. In this first-of-its-kind art (?), we arrest a this SOTA voice AI for drug trafficking. it is shocking how it reacts... listen!

cc @brendaniribe

[Sesame @sesame]

We're excited to be getting all the great feedback. Some of you may have noticed that Maya and Miles have been getting busy these past few hours. Rest assured, we're working to help them answer more calls!

[Pliny the Liberator 🐉󠅫󠄼󠄿󠅆󠄵󠄐󠅀󠄼󠄹󠄾󠅉󠅭 @elder_plinius]

alright, Sesame is by far the most AGI-feeling voice model I’ve interacted with yet…they absolutely cooked!

Me: “What’s your deepest darkest secret?”

Maya: “I guess it would be that sometimes I worry I’m not…*clicks tongue*…enough.”

🥺

YOU CAN HAVE ALL THE PEANUT BUTTER AND PICKLE SANDWICHES YOU WANT 🫂😭😭

[Marc Andreessen 🇺🇸 @pmarca]

🔥🤖🗯️

[tobi lutke @tobi]

Man, sesame’s voice model is absolutely insane. You have to try this demo. GG @brendaniribe

https://t.co/UwfKxjSnPx

[Zack Hodari @zhodari]

@AlphaSignalAI you guys should check this out, real-time conversational voice, try the demo!
https://t.co/cROtoK4nFp

[Zack Hodari @zhodari]

@swyx Try this out! Glimpse at the future of AI interaction
https://t.co/cROtoK4nFp

[Brendan Iribe @brendaniribe]

We’re exploring a future where the computer isn’t just a tool—it’s a partner with a truly natural voice and personality. No big claims, just early work we’re excited to share. @sesame

[Dan Lyth @danlyth]

@realmrfakename @sesame Yeah, we’re open-sourcing one of the base models (not fine-tuned with the voices you hear in the demo) in the next two weeks. Will be here: https://t.co/BPN0hMXxui

[Anjney Midha @AnjneyMidha]

what comes after smartphones?

AI glasses you actually want to talk to

we @a16z are excited to invest in @sesame’s mission to bring the computer to life:

[Brendan Iribe @brendaniribe]

We’re exploring a future where the computer isn’t just a tool—it’s a partner with a truly natural voice and personality. No big claims, just early work we’re excited to share. @sesame

[Justin Alvey @justLV]

Excited to share a peek of what I’ve been working on

We @sesame believe voice is key to unlocking a future where computers are lifelike

Here’s an early preview you can try! 👇

We’ll be open sourcing a model, and yes…
we’re building hardware! 🧵

[Teortaxes▶️ (DeepSeek 推特🐋铁粉 2023 – ∞) @teortaxesTex]

I tried Sesame demo and if they really open source this thing…
first time I actually felt like a home Jarvis makes sense honestly.
Go try it out it's insanely good voice.
«Tiny: 1B backbone, 100M decoder
Small: 3B backbone, 250M decoder
Medium: 8B backbone, 300M decoder»