Bland releases full-duplex speech model Tofu-1
Understand this story
Bland has released the full-duplex speech-to-speech model Tofu-1, currently in research preview and open to only a small number of enterprise slots. The model directly processes audio input and output without intermediate transcription, supports speaker tracking, noise separation, and recognition of paralinguistic information, and can be interrupted mid-call; it targets noisy call scenarios such as moving vehicles, hospital wards, and weak-signal lines. Bland lists banking, healthcare, insurance, and government as target industries, and says the enterprise preview will open in January next year. Bland has not disclosed the model's size, latency, or benchmark results.
AI overview based on source reports · Updated 6 hr ago
Coverage timeline
Follow the coverage to explore different perspectives.
- MarkTechPostBland Launches Tofu-1, a Full-Duplex Speech-to-Speech Model for Calls
Bland, the San Francisco voice-AI company, has released Tofu-1, a full-duplex speech-to-speech model in research preview that targets calls from moving cars, hospital rooms and weak-signal lines, listening while it speaks and reasoning while it talks. Bland lists speaker tracking, noise separation and paralinguistics as its audio skills, and says callers can interrupt or correct it mid-sentence while it keeps the conversation moving and reports results only when work is done. Access is a closed enterprise research preview for banking, healthcare, insurance and government, with Bland citing January availability and no published size, latency, pricing or benchmarks.
Activity for this story
- Current comparable activity
- 8
- Peak comparable activity
- 10Nov 15 19:00
- Change in the past 24 hours
- –
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.