Average Ratings 0 Ratings
Average Ratings 0 Ratings
Description
Sonic is an advanced text-to-speech model designed specifically for real-time voice agents, featuring a natural delivery system with a response time of less than 90 milliseconds and supporting over 40 languages seamlessly. Its primary aim is to facilitate effortless voice interactions, characterized by a tone that adapts to various contexts, a steady pacing, and speech that aligns with the natural flow of conversation. Sonic automatically interprets the emotional nuances within transcripts, adjusting its delivery accordingly, and allows for the direct insertion of non-verbal cues like laughter into the spoken text. Faithful to the original transcripts, the model generates clear audio across different languages and voice options while effortlessly managing alphanumeric data, including order and phone numbers, email addresses, and IDs, without requiring any prior processing. Its context-aware pronunciation ensures that heteronyms are articulated correctly based on surrounding terms, and customizable pronunciation dictionaries empower teams to dictate how specific proper nouns and industry-related terminology should be pronounced. This comprehensive approach not only enhances the quality of interactions but also tailors the user experience to meet diverse communication needs.
Description
Dessa is an innovative speech-to-speech AI model developed by Block, specifically designed for exploring conversational voice technologies and their various applications. This model uniquely processes audio inputs and generates audio outputs directly, bypassing the need for an intermediary text conversion. Instead of relying on text as a foundation, it has been built from the ground up using actual human conversations, enabling it to facilitate full-duplex communication, where it can listen and speak simultaneously. Designed to operate locally on advanced hardware like the MacBook Pro equipped with an M4 Max chip or superior, Dessa effectively captures nuanced conversational elements such as emotions, sarcasm, laughter, pauses, and turn-taking, which are often diminished in text-based communication systems. Aimed primarily at AI safety researchers and developers, it serves as a powerful tool for examining voice model dynamics, privacy implications, and the intricacies of real-time interactions. Importantly, Dessa is not intended for general business use or as a hosted voice-agent solution, marking its specific role in the realm of research and development within the voice technology landscape. This specificity underscores its potential to deepen understanding of voice interactions and inform future AI advancements.
API Access
Has API
Yes
API Access
Has API
No
Integrations
No details available.
Integrations
No details available.
Pricing Details
$5 per month
Free Trial
Yes
Free Version
Yes
Pricing Details
No price information available.
Free Trial
No
Free Version
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
Deployment
Web-Based
No
On-Premises
No
iPhone App
No
iPad App
No
Android App
No
Windows
No
Mac
Yes
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
Cartesia
Founded
2023
Country
United States
Website
www.cartesia.ai/sonic
Vendor Details
Company Name
Block
Founded
2009
Country
United States
Website
block.xyz/dessa