Cartesia Ink 2Cartesia
|
Tofu-1Bland
|
|||||
| Cartesia Ink 2 | Tofu-1 | |||||
|---|---|---|---|---|---|---|
Related Products
|
||||||
Cartesia Ink 2:
About
Ink 2 is Cartesia’s fastest, most accurate streaming speech-to-text model, built for production voice agents with the lowest word error rate and best turn detection of any streaming STT. It is designed to transcribe structured data such as phone numbers, dates, and emails correctly the first time, while also knowing when a speaker starts and finishes without requiring a separate voice activity detection system. Turn detection is built directly into the model, so voice agents can react to events instead of managing raw transcript segments. Ink 2 emits a full lifecycle of turn events, giving an agent clear signals for when to listen, interrupt, think, prepare a reply, cancel a premature response, or speak. The transcript property is cumulative within a turn, meaning each update contains the full text transcribed so far rather than a delta, and emitted text is final once sent.
|
Tofu-1:
About
Tofu-1 is Bland's full-duplex speech-to-speech model for voice calls. It processes audio directly, tracks speakers and who they are addressing, and is designed to distinguish a caller from overlapping speech and environmental sounds. The model can listen and respond at the same time, handle interruptions or corrections, and continue reasoning while a task is underway. It can also generate audio that includes multiple speakers and background sound. Bland presents Tofu-1 for high-stakes call workflows in banking, healthcare, insurance, and government, including claim, benefit, payment, and appointment interactions. The product is currently available through a limited research preview, with access requests open.
|
|||||
Cartesia Ink 2:
Platforms Supported
Windows
Not Supported
Mac
Not Supported
Linux
Not Supported
Cloud
Supported
On-Premises
Not Supported
iPhone
Not Supported
iPad
Not Supported
Android
Not Supported
Chromebook
Not Supported
|
Tofu-1:
Platforms Supported
Windows
Not Supported
Mac
Not Supported
Linux
Not Supported
Cloud
Supported
On-Premises
Not Supported
iPhone
Not Supported
iPad
Not Supported
Android
Not Supported
Chromebook
Not Supported
|
|||||
Cartesia Ink 2:
Audience
Developers and product teams that need fast, accurate streaming speech recognition and transcription for real-time voice applications
|
Tofu-1:
Audience
Teams building or operating high-stakes voice-call workflows in banking, healthcare, insurance, and government, including claim, benefit, payment, and appointment interactions.
|
|||||
Cartesia Ink 2:
Support
Phone Support
Not Supported
24/7 Live Support
Not Supported
Online
Supported
|
Tofu-1:
Support
Phone Support
Not Supported
24/7 Live Support
Not Supported
Online
Not Supported
|
|||||
Cartesia Ink 2:
API
Offers API
Supported
|
Tofu-1:
API
Offers API
Not Supported
|
|||||
Cartesia Ink 2:
Screenshots and Videos |
Tofu-1:
Screenshots and VideosNo images available
|
|||||
Cartesia Ink 2:
Pricing
No information available.
Free Version
Not Supported
Free Trial
Not Supported
|
Tofu-1:
Pricing
No information available.
Free Version
Not Supported
Free Trial
Not Supported
|
|||||
Cartesia Ink 2:
Reviews/
|
Tofu-1:
Reviews/
|
|||||
Cartesia Ink 2:
Training
Documentation
Supported
Webinars
Not Supported
Live Online
Not Supported
In Person
Not Supported
|
Tofu-1:
Training
Documentation
Not Supported
Webinars
Not Supported
Live Online
Not Supported
In Person
Not Supported
|
|||||
Cartesia Ink 2:
Company InformationCartesia
Founded: 2023
United States
docs.cartesia.ai/build-with-cartesia/stt/latest
|
Tofu-1:
Company InformationBland
Founded: 2023
United States
www.bland.ai/speech-to-speech
|
|||||
Cartesia Ink 2:
Alternatives |
Tofu-1:
Alternatives |
|||||
| Cartesia Ink 2: |
Tofu-1:
|
|||||
|
Cartesia Ink 2:
|
Tofu-1:
|
|||||
|
Cartesia Ink 2:
|
Tofu-1:
|
|||||
|
Cartesia Ink 2:
|
Tofu-1:
|
|||||
Cartesia Ink 2:
Categories |
Tofu-1:
Categories |
|||||
| Cartesia Ink 2: |
Tofu-1:
Integrations
MachinesFluent
Not Supported
|
|||||
|
Cartesia Ink 2:
|
Tofu-1:
|