Average Ratings 0 Ratings
Average Ratings 0 Ratings
Description
MAI-Voice-2.1 is a text-to-speech solution provided by Microsoft, designed specifically for developers working on voice-driven applications. This model produces articulate and expressive speech from written text, supports a diverse range of 23 languages, and includes features for controlling emotion and style. Additionally, it ensures consistency for long-form speech and provides gated matches to approved reference voices. Developers can utilize it via the Microsoft Foundry and the Azure Speech APIs and SDKs, making it suitable for various uses, including narration, audiobooks, voice assistant integration, and enhancing customer service interactions. Furthermore, its versatility allows for a wide range of applications in modern technology.
Description
Utilize a browser equipped with in-app prompts alongside a recording tool to gather audio samples. You can access a curated collection of phonetically balanced sentences designed to help build a 30-minute dataset aimed at training a TTS model that captures the nuances of your distinct voice. Tailor the model's sound by selecting the pitch range that aligns best with your vocal characteristics, as a suggested typical voice pitch range setting is already included, along with a preconfigured optimal recipe for personalizing the TTS model to reflect your voice. To further enhance functionality, create an API that allows seamless integration of your customized TTS model into various applications. You’ll also have the option to download a deployable package that includes a helm chart, facilitating deployment on any cloud platform or an on-premises Kubernetes cluster. Following that, you can effortlessly host your voice microservice using NVIDIA or implement it with a simple line of code, ensuring smooth operation. Additionally, the Riva TTS model can be set up, customized, and deployed through user-friendly no-code, end-to-end graphical workflows, eliminating the need for intricate infrastructure configuration, and making the process accessible for everyone. This approach not only streamlines the deployment process but also empowers users to create high-quality TTS solutions with minimal technical barriers.
API Access
Has API
Yes
API Access
Has API
Yes
Screenshots View All
No images available
Integrations
Azure AI Speech
Yes
Azure Marketplace
No
Kubernetes
No
NVIDIA TensorRT
No
Integrations
Azure AI Speech
No
Azure Marketplace
Yes
Kubernetes
Yes
NVIDIA TensorRT
Yes
Pricing Details
$22/1M characters
Usage-based at $22 per 1 million characters of generated speech.
Free Trial
No
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
No
Customer Support
Business Hours
Yes
Live Rep (24/7)
No
Online Support
Yes
Types of Training
Training Docs
No
Webinars
No
Live Training (Online)
No
In Person
No
Types of Training
Training Docs
Yes
Webinars
Yes
Live Training (Online)
No
In Person
No
Vendor Details
Company Name
Microsoft
Founded
1975
Country
United States
Website
microsoft.ai/models/mai-voice-2-1/
Vendor Details
Company Name
NVIDIA
Founded
1993
Country
United States
Website
www.nvidia.com/en-us/gpu-cloud/riva-studio/
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
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