Average Ratings 0 Ratings
Average Ratings 0 Ratings
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
Create robust AI applications suitable for enterprises in just minutes, all without the need for coding, using the Katonic generative AI platform. Enhance employee productivity and elevate customer experiences through the capabilities of generative AI. Develop chatbots and digital assistants that effortlessly retrieve and interpret data from documents or dynamic content, refreshed automatically via built-in connectors. Seamlessly identify and extract critical information from unstructured text while uncovering insights in specific fields without the requirement for any templates. Convert complex text into tailored executive summaries, highlighting essential points from financial analyses, meeting notes, and beyond. Additionally, implement recommendation systems designed to propose products, services, or content to users based on their historical interactions and preferences, ensuring a more personalized experience. This innovative approach not only streamlines workflows but also significantly improves engagement with customers and stakeholders alike.
API Access
Has API
Yes
API Access
Has API
No
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
Yes
Types of Training
Training Docs
Yes
Webinars
No
Live Training (Online)
No
In Person
No
Types of Training
Training Docs
Yes
Webinars
Yes
Live Training (Online)
Yes
In Person
No
Vendor Details
Company Name
Decibri
Founded
2026
Country
Australia
Website
decibri.com
Vendor Details
Company Name
Katonic
Founded
2020
Country
Australia
Website
www.katonic.ai/