Moses Oh

Research @GoogleDeepmind
Previously @hume_ai (EVI3/2/1, Octave)

[Hume AI @hume_ai]

Introducing Octave 2: our next-generation multilingual text-to-speech model

What’s new:
- Fluent in 11+ languages
- 40% faster (<200ms latency⁠⁠) & 50% cheaper than Octave 1
- Multi-speaker conversation
- More reliable pronunciation
- New voice conversion & phoneme editing capabilities

For the month of October, we’re offering 50% off our Creator plan - use code OCTAVE2 at checkout!

[Moses Oh @MosesOh4]

@daniel_jun_oh @Nature congrats!!

[Jun Young (Daniel) Oh @daniel_jun_oh]

Excited to share my co-first paper at @Nature! I would like to thank my co-first authors Jason and Heydar and Prof. Dan Dombeck for his amazing mentorship. I hope that this work can open up future investigations of the underlying neural mechanisms of representation drift!

[Moses Oh @MosesOh4]

@hume_ai @OpenAI create your own clone :)
https://t.co/D7FQJ4MRF2

[Moses Oh @MosesOh4]

Cloned OpenAI AVM with a 10s clip 😎
Give it a try - https://t.co/WlUHSRBUkc

@hume_ai @OpenAI

[Hume AI @hume_ai]

2024: Voice Cloning
2025: What about personality cloning?

Hume’s voice AI can now not only mimic your voice but also speaking style and language.

It’s now available via our TTS and new speech-to-speech model, EVI 3, which is also launching today.

[Axios @axios]

.@hume_ai's @gagnecr13 &amp; @inafried test out Hume AI's EVI 3 AI model that's optimized to understand and express human emotions at #AxiosAISummit

[Moses Oh @MosesOh4]

We released our new conversational speech-llm. Fully multimodal (inputting/outputting text&amp;audio tokens). Ability to adopt any voice, modulate speech, and generate language.

[Hume AI @hume_ai]

Meet EVI 3, another step toward general voice intelligence.

EVI 3 is a speech-language model that can understand and generate any human voice, not just a handful of speakers. With this broader voice intelligence comes greater expressiveness and a deeper understanding of tune, rhythm, timbre, and speaking style.

[Moses Oh @MosesOh4]

@lyronctk @a16zcrypto Congrats Lyron!!! 🤩

[Moses Oh @MosesOh4]

Literally blown away hearing our model. Amazing work from everyone at Hume. And extra kudos to the research team 🙂

[Hume AI @hume_ai]

Today, we’re releasing Octave: the first LLM built for text-to-speech.

🎨Design any voice with a prompt
🎬 Give acting instructions to control emotion and delivery (sarcasm, whispering, etc.)
🛠️Produce long-form content on our Creator Studio

Unlike traditional TTS that just “reads” words aloud, Octave understands how meaning affects delivery to generate emotional, human-like speech.

[Moses Oh @MosesOh4]

@hume_ai Wait … are all the voices in this video AI generated?

[Joseph (Jun) Oh @josephoh0517]

Grateful to train with awesome chiefs like @AF_Haddad. Come check us out at @NeurosurgUCSF ! #subi #neurosurgery

[Moses Oh @MosesOh4]

we have NotebookLM at home 🥲

[Hume AI @hume_ai]

Multiple interacting AI speakers:

OCTAVE can generate multiple, consistent AI personas within a real-time conversation

[Moses Oh @MosesOh4]

Excited to share what I've been working on! Over the past few months, we’ve been aligning language and speech both semantically and non-semantically in a fully trained multimodal model, while maintaining language capabilities.

[Hume AI @hume_ai]

Introducing OCTAVE, a next-generation speech-language model.

OCTAVE has new emergent capabilities, like on-the-fly voice and personality creation and much more 👇

[Moses Oh @MosesOh4]

It was great running into old Magenta folks at Neurips! @jesseengel @jpgard @wilzh40 @douglas_eck @GoogleMagenta

[WIRED @WIRED]

Hume AI, a startup founded by a psychologist who specializes in measuring emotion, gives some top large language models a realistic human voice. https://t.co/BASqQRBbGE

[Hume AI @hume_ai]

Introducing Empathic Voice Interface 2 (EVI 2), our new voice-to-voice foundation model. EVI 2 merges language and voice into a single model trained specifically for emotional intelligence.

You can try it and start building today.

[Guillermo Rauch @rauchg]

We’ll probably look back on Her as the most accurately predictive sci-fi movie of our generation.

Personal (even intimate), long-context, always-on AI assistants are happening.

It feels like https://t.co/uj9nfZSStQ this week filled the missing piece of the puzzle.

[Moses Oh @MosesOh4]

Personal AI tutor makes learning enjoyable! Esp one that can understand non-verbal confusion 🤯 @hume_ai https://t.co/D7FQJ4MRF2

[Moses Oh @MosesOh4]

@hume_ai @josephoh0517 i got 2 brothers AND a sister 😱