Average Ratings 0 Ratings
Average Ratings 0 Ratings
Description
Canopy Labs has unveiled Orpheus, an innovative suite of advanced speech large language models (LLMs) aimed at achieving human-like speech generation capabilities. Utilizing the Llama-3 architecture, these models have been trained on an extensive dataset comprising over 100,000 hours of English speech, allowing them to generate speech that exhibits natural intonation, emotional depth, and rhythmic flow that outperforms existing high-end closed-source alternatives. Orpheus also features zero-shot voice cloning, enabling users to mimic voices without any need for prior fine-tuning, and provides easy-to-use tags for controlling emotion and intonation. The models are engineered for low latency, achieving approximately 200ms streaming latency for real-time usage, which can be further decreased to around 100ms when utilizing input streaming. Canopy Labs has made available both pre-trained and fine-tuned models with 3 billion parameters under the flexible Apache 2.0 license, with future intentions to offer smaller models with 1 billion, 400 million, and 150 million parameters to cater to devices with limited resources. This strategic move is expected to broaden accessibility and application potential across various platforms and use cases.
Description
Vokaturi software exemplifies cutting-edge technology in recognizing emotions through vocal cues. Crafted and continually refined by Paul Boersma, a professor at the University of Amsterdam and the chief creator of the renowned speech analysis tool Praat, its algorithms are at the forefront of this field. This innovative software can accurately assess whether a speaker is feeling happy, sad, fearful, angry, or neutral based solely on their voice. The open-source variant of Vokaturi provides impressive accuracy in distinguishing these five emotions, even when encountering a speaker for the first time. In contrast, the "plus" version offers performance that rivals that of an experienced human listener. Developers have the option to seamlessly integrate Vokaturi into their applications, making it a versatile tool for various uses. Licensing options are flexible, allowing users to select either a free open-source license or a paid one for enhanced features. Overall, Vokaturi presents an accessible yet powerful solution for emotion recognition in voice applications.
API Access
Has API
No
API Access
Has API
Yes
Integrations
Baseten
Yes
GitHub
Yes
Google Colab
Yes
Hugging Face
Yes
Llama 3
Yes
VoiSpark
Yes
Integrations
Baseten
No
GitHub
No
Google Colab
No
Hugging Face
No
Llama 3
No
VoiSpark
No
Pricing Details
No price information available.
Free Trial
Yes
Free Version
No
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
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)
Yes
In Person
No
Types of Training
Training Docs
Yes
Webinars
No
Live Training (Online)
No
In Person
No
Vendor Details
Company Name
Canopy Labs
Country
United States
Website
canopylabs.ai/model-releases
Vendor Details
Company Name
Vokaturi
Founded
2016
Website
vokaturi.com
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
Product Features
Emotion Recognition
Facial Emotions
No
Facial Expression Analysis
No
Machine Learning
No
Photo Emotions
No
Speech Emotions
No
Video Emotions
No
Written Text Emotions
No