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
Qwen3-TTS represents an innovative collection of advanced text-to-speech models created by the Qwen team at Alibaba Cloud, released under the Apache-2.0 license, which delivers stable, expressive, and real-time speech output with functionalities like voice cloning, voice design, and precise control over prosody and acoustic features. This suite supports ten prominent languages—Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, and Italian—along with various dialect-specific voice profiles, enabling adaptive management of tone, speech rate, and emotional delivery tailored to text semantics and user instructions. The architecture of Qwen3-TTS incorporates efficient tokenization and a dual-track design, facilitating ultra-low-latency streaming synthesis, with the first audio packet generated in approximately 97 milliseconds, making it ideal for interactive and real-time applications. Additionally, the range of models available offers diverse capabilities, such as rapid three-second voice cloning, customization of voice timbres, and voice design based on given instructions, ensuring versatility for users in many different scenarios. This flexibility in design and performance highlights the model's potential for a wide array of applications in both commercial and personal contexts.
API Access
Has API
Yes
API Access
Has API
Yes
Pricing Details
$22 per month
Free Trial
No
Free Version
Yes
Pricing Details
Free
Free Trial
No
Free Version
Yes
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
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
No
Live Training (Online)
Yes
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
github.com/QwenLM/Qwen3-TTS
Product Features
Product Features
Text to Speech
API
No
Adjust Speaking Rate / Pitch
No
Audio Optimization
No
Custom Lexicons
No
Different Voice Choices
No
Multi-Language Support
No
Synchronize Speech
No