Skip to content
AIBRAINWORX / THE INDEPENDENT AI LABRESEARCH · HARDWARE · OPEN INTELLIGENCE
AI News / Model Watch

Bland opens Tofu-1 enterprise preview for full-duplex speech-to-speech calls

The closed research preview bypasses intermediate speech-to-text transcripts to handle interruptions, tone, and noisy phone lines directly.

Official Bland AI wordmark graphic from bland.ai
Bland AI, official site social preview graphic from bland.ai; identification only, no endorsement.
Event / context: Bland announced the Tofu-1 closed enterprise research preview in November 2026.. Source check: October 28, 2026.

Voice-AI company Bland has opened an enterprise research preview for Tofu-1, a full-duplex speech-to-speech model designed for live telephone workflows in sectors such as healthcare, insurance, and banking. Unlike conventional voice pipelines that chain speech-to-text, an LLM, and text-to-speech, Tofu-1 processes and generates audio directly without an intermediate text transcript.

Full-duplex handling and noisy environments

According to Bland's announcement, removing the text bottleneck lets the model listen and speak simultaneously, so callers can interrupt or redirect the agent mid-sentence while background tool calls or database lookups run in parallel. The architecture is also tuned to preserve acoustic cues such as hesitation and urgency and to separate speaker audio from car, home, or hospital background noise.

Availability and verification limits

Tofu-1 is currently restricted to an application-based closed enterprise research preview on Bland's platform. No public API pricing, open weights, latency benchmarks, or independent evaluations in regulated environments have been published. For clinical or safety-sensitive phone lines, real-world reliability and compliance remain unverified outside vendor testing.

Original reporting; sources reviewed November 16, 2026. Closed research preview; no hands-on testing claimed.

Follow your curiosity.

Pass the signal.