Bland Releases Tofu-1 Full-Duplex Speech Model for Phone Calls
Start here
Bland, a San Francisco voice-AI company, released Tofu-1, a full-duplex speech-to-speech model in research preview that processes audio in and audio out during phone calls without an intermediate transcript. Bland says the model tracks speakers, filters background noise such as traffic or hospital intercoms, and picks up hesitation and urgency, and that it keeps talking while a request is processed. Access is a closed enterprise preview limited to a small number of companies in banking, healthcare, insurance and government, with Bland citing January availability. Bland has not published parameter count, latency, pricing or benchmark results, so the claimed capabilities remain the company's own description rather than independently verified performance.
Generated from reports · updated 22 h ago
Report timeline
Follow the reports to see the event from different sides.
- MarkTechPostBland Launches Tofu-1, a Full-Duplex Speech-to-Speech Model for Phone Calls
Bland released Tofu-1, a full-duplex speech-to-speech model in research preview that handles audio in and audio out during phone calls without an intermediate transcript. Bland says the model tracks speakers, separates background noise such as traffic or hospital intercoms, and picks up hesitation and urgency, and it keeps talking while a request is processed. Access is limited to a small number of enterprises in banking, healthcare, insurance and government, with Bland citing January availability; no parameter count, latency, pricing or benchmark results have been published.
Heat for this event
- Current, comparable range
- 5
- Peak, comparable range
- 10November 15 19:00
- Change in 24 hours
- –
The trend compares the same participants over hours observed continuously, so its range can be narrower than the current heat count. Hover or tap the chart for hourly heat; the arrow keys move through it.