Audiogram: speech recognition and synthesis

Make your bot, smart assistant or speaker
sound recognizable and exclusive
Find a voice
for your brand
Use speech synthesis and recognition platform to create voice interface solutions
01
02

Details

Audiogram is a neural network-based speech recognition and synthesis platform

Smart Speech Recognition
A set of ML-models operating under challenging noise conditions fits for general and specific speech recognition tasks – in telecom, banking, healthcare and retail
Smart Speech Recognition
Book voice over
Voiceover with one of four synthesized voices, automatic pauses and speech effects marked up with embedded context-aware ML-model
Book voice over
Advanced Speech Synthesis
Fine-tuning of pitch and stress parameters with SSML helps to create an unique voice with a natural sounding
Advanced Speech Synthesis
High Recognition Rate
ASR offline bandwidth: 700 RTF with 512 Gb RAM usage, ASR online – 500 RTF with 128 Gb RAM usage
High Recognition Rate
Convenient Integration
gRPC API for direct interface with the platform or a set of connectors for conversion to other protocols: SIP, UniMRCP, REST (WebSocket)
Convenient Integration
MTS AI Product Sync'ing 
Audiogram is integrated with NLP platform and AI communication analysis — services for B2C communication management 
Learn more
MTS AI Product Sync'ing 
Data Security 
Installed on the customer's servers, the platform features a full range of functions and capabilities without any data leakage threats
Data Security 
Flexible Licensing
Audiogram offers the pay-as-you-go system to pay per minute of speech to text ai and per million characters of text-to-speech, package payments are also available
Flexible Licensing

Documentation

Please review all technical parameters in detail
557.68 KB
Audiogram White Paper
557.68 KB

Where is this used?

Speech technology that advances speech management options

Call Center Automation
IVR guides users, voice bots give prompts to operators, call customers and analyze dialogues 
Software & Game Dev
Integrating speech recognition and synthesis functions into end-user programs, voiceover for computer game characters and voice prompts
Making Audiobooks
Converting large volumes of text to speech with pauses and speech effects marked up with context-aware ML-model
Web and Media
Creating subtitles for videos, voiceover for article narration, transcription of interviews and single or multiple keynote speaker conferences
Social Network and Messengers 
Transcription of users' voicemail messages, text-to-speech reader and subtitle generator for videos
Voice Assistants
Smart Home and smart speaker assistants understand users and talk to them with speech synthesis and recognition modules
EdTech Companies
Transcription of audio and video lectures, subtitle generation, voiceover for course videos and articles
Transport & Retail
Voiceover of advertising and informational messages, generation of voice prompts for comfortable visitors navigation
Call Center Automation
IVR guides users, voice bots give prompts to operators, call customers and analyze dialogues 
Software & Game Dev
Integrating speech recognition and synthesis functions into end-user programs, voiceover for computer game characters and voice prompts
Making Audiobooks
Converting large volumes of text to speech with pauses and speech effects marked up with context-aware ML-model
Web and Media
Creating subtitles for videos, voiceover for article narration, transcription of interviews and single or multiple keynote speaker conferences
Social Network and Messengers 
Transcription of users' voicemail messages, text-to-speech reader and subtitle generator for videos
Voice Assistants
Smart Home and smart speaker assistants understand users and talk to them with speech synthesis and recognition modules
EdTech Companies
Transcription of audio and video lectures, subtitle generation, voiceover for course videos and articles
Transport & Retail
Voiceover of advertising and informational messages, generation of voice prompts for comfortable visitors navigation
Licensing

Pricing options

01

Pay as you go

Cloud hosting: fee per minute of audio recognition and per each million characters synthesis

02

Package

On-premise hosting: fee for a limited amount of speech recognition and synthesis minutes or for the number of streams

Personal price calculation

For personal price calculation, please submit your request and fill out the questionnaire you will receive in our response letter

Leave a request

Want to know more?

Leave a request, we will send you a commercial offer indicating the pricing with recommendations for solving your business problems

Want to know more?

Leave a request, we will send you a commercial offer indicating the pricing with recommendations for solving your business problems

Request demo

Enter Name
Enter email
Check phone number
Enter a link to the company website
News
Read more
Cases
MTS AI Adds Spam Calls Transcript Feature to MTS service
Tech
NLP Researchers Create Paraphrase Identification Dataset
Solutions
Voice and Text Bots Transforming the Customer Service
Cases
Using Audiogram to Develop AI Operator for MTS Call Center
Tech
Chatbots and Their Ability to Talk about Anything
Team news
MTS AI developer becomes prize winner in Yandex Cup championship
We use cookies to ensure you get the best experience on our website.
Full details about the “cookies”, what they are and how to opt out, can be found in the Cookies policy You may accept all cookies, disable them, or choose only the ones you consider as acceptable.
Configure Accept all