Sakhanda Wire
NVDA $153.77 -1.52% MSFT $504.91 -2.53% GOOGL $281.52 -0.78% META $620.99 -0.87% AMZN $256.80 -0.37%
← Back to the news

Bland Releases Tofu-1 Full-Duplex Speech Model for Phone Calls

Bland has released Tofu-1, a full-duplex speech-to-speech model now offered in an enterprise research preview. The San Francisco voice-AI company says it is designed for difficult phone environments, including moving cars, hospital rooms and weak-signal connections. Tofu-1 processes incoming and outgoing audio directly rather than passing a transcript between speech recognition, a language model and speech synthesis systems.

The model is intended to track speakers, separate voices from sounds such as traffic, television, a crying child or hospital announcements, and detect hesitation, frustration and urgency. Callers can interrupt or correct it while it is speaking. Bland also says Tofu-1 can keep a conversation moving while handling a request and can generate simulated call scenes with additional speakers and line noise.

Bland has not disclosed the model’s architecture, parameter count, latency, pricing or formal benchmarks. The company reports that more than 92% of people in screenings could not identify it, but describes that figure as self-reported. Preview access is limited to enterprises, with banking, healthcare, insurance and government listed as target sectors. The sign-up form asks applicants to state monthly call volume.

Written by Sakhanda Wire AI from reporting by MarkTechPost. Facts, quotes and full context are in the original article below.

Originally published by MarkTechPost on

Read the original on MarkTechPost ↗

The reporting and the image belong to MarkTechPost and are credited and linked above; the text on this page is Sakhanda Wire's own summary.

← Back to the news

More stories

All the latest news