Tofu-1
Tofu-1 is a watchlist entry, not a production pick; wait for published weights, API access, pricing, context, and benchmarks before planning a migration.
- Availability
- Announced - not yet released
- Family
- Tofu
- Released
- 2026-11-13
- Specialization
- realtime-voice
- Openness
- Proprietary
- License
- ProprietaryRestricted
- Weights
- Not released
- Code
- Unknown
No tracked provider pricing is available yet.
About
Tofu-1 is Bland's first speech-to-speech model, announced November 13, 2026 as a research preview for high-stakes enterprise phone calls. It is full duplex: it works on the call audio directly, listens while it speaks so callers can interrupt or correct it mid-sentence, and keeps the conversation going while it works on a request. Bland says it tells speakers apart, recognizes who a phrase is addressed to, separates the caller from background speech such as a television, and can also generate multi-speaker audio with background sound.
Providers
No active provider routes are tracked for this model yet.
Capabilities
Benchmark peer barsfor Vision
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.