Average Ratings 0 Ratings

Total 0 out of 5 stars
ease 0 out of 5 stars
features 0 out of 5 stars
design 0 out of 5 stars
support 0 out of 5 stars

No User Reviews. Be the first to provide a review:

Write a Review

Average Ratings 0 Ratings

Total 0 out of 5 stars
ease 0 out of 5 stars
features 0 out of 5 stars
design 0 out of 5 stars
support 0 out of 5 stars

No User Reviews. Be the first to provide a review:

Write a Review

Description

Decibri is an audio library written in Rust, aimed at developers focused on creating applications for real-time speech, voice agents, and audio processing. It includes functionalities for microphone input, speaker output, PCM streaming, and handling audio files, along with a command-line interface that supports Python, Node.js, Rust, and browser APIs. Among its many features are voice activity detection, acoustic echo cancellation, and optional enhancements such as denoising, filtering, automatic gain control, and limiting. Developers have the capability to stream audio they capture to either cloud or local speech-to-text services, while also playing back synthesized speech through its audio output systems. The library can be utilized in various scenarios, including the development of voice assistants, transcription services, conversational agents, wake-word detection, interactive robotics applications, full-duplex speech systems, audio processing pipelines, and for use in edge devices. It offers prebuilt native packages compatible with Windows, macOS, and Linux, and the Python and Node.js implementations do not require any additional build tools for setup. Additionally, the browser version allows for audio capture, energy-based speech detection, and playback, expanding its accessibility and usability across different platforms. This versatility makes Decibri a powerful tool in the realm of audio application development.

Description

Tofu-1 represents Bland's innovative full-duplex speech-to-speech model tailored for voice communication. This advanced system directly processes audio, effectively identifies speakers and their intended audience, and excels at differentiating a caller's voice amidst competing speech and ambient noises. Additionally, it possesses the capability to listen and reply simultaneously, manage interruptions or corrections seamlessly, and maintain its reasoning process while tasks are being performed. The model can also synthesize audio featuring multiple voices along with background sounds, making it versatile for various applications. Bland showcases Tofu-1 as an essential tool for critical call workflows across sectors such as banking, healthcare, insurance, and government, specifically in scenarios involving claims, benefits, payments, and appointments. Currently, the product is accessible through a limited research preview, allowing interested parties to submit requests for access. Furthermore, the potential applications of Tofu-1 could significantly enhance communication efficiency in high-demand environments.

API Access

Has API Yes 

API Access

Has API No 

Screenshots View All

Screenshots View All

No images available

Integrations

Amazon Transcribe Yes 
AssemblyAI Yes 
Azure AI Speech Yes 
Deepgram Yes 
Google Cloud Speech-to-Text Yes 
OpenAI Realtime API Yes 
Voxtral Yes 

Integrations

Amazon Transcribe No 
AssemblyAI No 
Azure AI Speech No 
Deepgram No 
Google Cloud Speech-to-Text No 
OpenAI Realtime API No 
Voxtral No 

Pricing Details

$0
The core audio library is free under Apache-2.0. Fees for cloud speech-service providers are separate.
Free Trial No 
Free Version Yes 

Pricing Details

No price information available.
Free Trial No 
Free Version No 

Deployment

Web-Based No 
On-Premises Yes 
iPhone App No 
iPad App No 
Android App No 
Windows Yes 
Mac Yes 
Linux Yes 
Chromebook No 

Deployment

Web-Based Yes 
On-Premises No 
iPhone App No 
iPad App No 
Android App No 
Windows No 
Mac No 
Linux No 
Chromebook No 

Customer Support

Business Hours No 
Live Rep (24/7) No 
Online Support Yes 

Customer Support

Business Hours No 
Live Rep (24/7) No 
Online Support No 

Types of Training

Training Docs Yes 
Webinars No 
Live Training (Online) No 
In Person No 

Types of Training

Training Docs No 
Webinars No 
Live Training (Online) No 
In Person No 

Vendor Details

Company Name

Decibri

Founded

2026

Country

Australia

Website

decibri.com

Vendor Details

Company Name

Bland

Founded

2023

Country

United States

Website

www.bland.ai/speech-to-speech

Product Features

Product Features

Alternatives

Seeduplex Reviews

Seeduplex

ByteDance

Alternatives

Azure AI Speech Reviews

Azure AI Speech

Microsoft
Dessa Reviews

Dessa

Block
Dessa Reviews

Dessa

Block
Seeduplex Reviews

Seeduplex

ByteDance