AI company Sesame has released the base model that powers Maya, the impressively realistic voice assistant.
The model, which is 1 billion parameters in size (“parameters” referring to individual components of the model), is under an Apache 2.0 license, meaning it can be used commercially with few restrictions. Called CSM-1B, the model generates “RVQ audio codes” from text and audio inputs, according to Sesame’s description on the AI dev platform Hugging Face.
RVQ refers to “residual vector quantization,” a technique for encoding audio into discrete tokens called codes. RVQ is used in a number of recent AI audio technologies, including Google’s SoundStream and Meta’s Encodec.
CSM-1B uses a model from Meta’s Llama family as its backbone paired with an audio “decoder” component. A fine-tuned variant of CSM powers Maya, Sesame says.
“The model open-sourced here is a base generation model,” Sesame writes in CSM-1B’s Hugging Face and GitHub repositories. “It is capable of producing a variety of voices, but it has not been fine-tuned on any specific voice […] The model has some capacity for non-English languages due to data contamination in the training data, but it likely won’t do well.”
It’s unclear what data Sesame used to train CSM-1B. The company didn’t say.
The model has no real safeguards to speak of, it’s worth noting. It’s an “honor system” situation. Sesame is merely urging developers and users not to use the model to mimic a person’s voice without their consent, create misleading content like fake news, or engage in “harmful” or “malicious” activities.
I tried the demo on Hugging Face, and cloning my voice took less than a minute. From there, it was easy to generate speech to my heart’s desire, including on controversial topics like the election and Russian propaganda:
Sesame, co-founded by Oculus co-creator Brendan Iribe, went viral in late February for its assistant tech, which comes close to clearing uncanny valley territory. Maya and Sesame’s other assistant, Miles, take breaths and speak with disfluencies, and can be interrupted while speaking, much like OpenAI’s Voice Mode.
Sesame has raised an undisclosed amount of capital from Andreessen Horowitz, Spark Capital, and Matrix Partners. In addition to building voice assistant tech, the company says it’s prototyping AI glasses “designed to be worn all day” that’ll be equipped with its custom models.
