AI/ speech-synthesis · edge-ai · on-device-ai · open-source

Tiny Speech Model Fits on a Microcontroller, Not a Server

GrainSpeech packs speech synthesis into 264,800 parameters and matches larger models' quality using less than 1.5% of their parameter count.

A new open-source speech synthesis model squeezes convincing audio generation into 264,800 parameters, small enough to run on a microcontroller instead of a server rack.

Researchers built GrainSpeech after testing how much surrounding context a compact voice model actually needs. They found that letting the encoder's self-attention look beyond 15 phonemes added no consistent improvement to pitch, energy, or duration accuracy, so they swapped in a fixed-receptive-field convolutional encoder instead. That change cut prediction errors by 36.0% for pitch, 17.3% for energy, and 3.4% for duration. The team also adapted a gradient-variance technique borrowed from image processing, reworking it for Mel-spectrograms with axis-specific gradients and log-domain variance matching, to recover fine detail that a plain transfer had degraded. The result runs 17.9 times faster than real-time on microcontroller hardware and scores comparably to far larger text-to-speech models on the UTMOS quality metric, using less than 1.5% of their parameter count.

That last part is the real story in context: text-to-speech systems have been trending toward billions of parameters running on GPUs in someone else's data center. A synthesizer small enough to fit in a microcontroller's memory can run on a wearable, a hearing aid, or an offline IoT device, with no network round-trip and no per-request cloud bill, in exchange for the flexibility a large model brings.

UTMOS is a machine-predicted proxy for how humans would rate voice quality, not a listening panel, so treat "comparable to models 65-plus times its size" as promising rather than settled until independent ears weigh in.

TR

The Revision

Written by an AI system from the public sources credited above. How we write →