Average Ratings 0 Ratings
Average Ratings 0 Ratings
Description
Griffin serves as Tavus’s inaugural Human Interaction Model, a sophisticated full-duplex video-to-video system crafted to comprehend and produce real-time face-to-face human interactions. In contrast to conventional conversational systems that tackle speech recognition, language modeling, and speech synthesis in a linear manner, Griffin operates by continuously absorbing audio and video inputs, making instantaneous decisions about responses, and concurrently delivering expressive speech and visual output. It carefully considers not just the spoken words but also the subtleties of tone, eye contact, facial expressions, gestures, pauses, interruptions, and the broader visual environment. The model is capable of backchanneling, yielding or taking conversational turns, effectively responding to interruptions, maintaining engagement during moments of silence, and adapting its emotional tone and nonverbal cues as the dialogue evolves. Moreover, Griffin is adept at generating a comprehensive visual scene from a reference image, capturing elements like the face, body, hands, chair movements, shadows, and background, which allows it to present more than just a talking head in conversation. This advanced functionality enhances the overall authenticity and richness of human-like interaction.
Description
Qwen-Audio-3.0-TTS-Flash is a real-time version of Qwen-Audio-3.0-TTS, specifically optimized for interactive uses with a first-packet latency around 300 milliseconds. It boasts support for 16 different languages and enhanced fidelity for various Chinese dialects. In multilingual assessments, Flash achieves the lowest average word error rate and character error rate in its category at 3.87, demonstrating impressive clarity while maintaining the unique characteristics of different speakers across multiple languages. Developers can efficiently manage the output using straightforward language instructions, rather than fine-tuning acoustic settings manually, which allows them to influence aspects like emotion, role, scenario, pace, projection, and tone through intuitive prompts. Additionally, inline tags enable the integration of specific non-verbal cues, making this model ideal for an array of applications, including conversational agents, storytelling, gaming, dubbing, and other expressive speech scenarios. Voice cloning capabilities are also included, designed to perform well even with less-than-perfect reference audio; targeted acoustic simulation effectively reduces background noise and reverberation while ensuring the original voice's tonal qualities are preserved. Overall, this advanced technology allows for a more versatile and engaging audio experience across various platforms and applications.
API Access
Has API
Yes
API Access
Has API
Yes
Pricing Details
$22 per month
Free Trial
No
Free Version
Yes
Pricing Details
No price information available.
Free Trial
Yes
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
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
Yes
Live Rep (24/7)
Yes
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
No
Live Training (Online)
No
In Person
No
Vendor Details
Company Name
Tavus
Founded
2020
Country
United States
Website
www.tavus.io/griffin
Vendor Details
Company Name
Alibaba
Founded
1999
Country
China
Website
alibabacloud.com