TURN TEXT INTO SPEECH WITH GOOGLE'S API
NET|April 2020
Richard Mattka introduces you to the field of AI speech synthesis using Google’s new neural-network powered Text-to-Speech API
Richard Mattka
TURN TEXT INTO SPEECH WITH GOOGLE'S API

Artificial intelligence has become part of nearly every aspect of our lives, from content-aware fills for video and photos, facial recognition to unlock your phone and even recommendations for your mobile coffee order. The field is growing so rapidly, it’s becoming increasingly difficult to nail down a definitive definition. Machine learning, deep learning, natural language processing (NLP), computer vision, voice recognition and speech synthesis… all these and many more fall under the umbrella of artificial intelligence.

IBM, Google, Amazon and many others have created API endpoints for developers to integrate and start leveraging AI in their own projects. AI trained on millions of data sets and models are at your fingertips. Hooking into machine learning power has never been easier.

Imagine building a web-based app that can not only understand what a user is saying to it, but also respond in a voice customised to their liking. All in real time. Combining chatbot dialog models with voice recognition and now voice synthesis, this scenario has become a reality. You can develop solutions for education, hands-free communications, call-centre automation and engaging games and web experiences.

In this tutorial, you are going to create a simple app to enable you to return AI-powered, human-sounding speech, based on values you choose.

SPEECH SYNTHESIS (TEXT-TO-SPEECH)

Speech synthesis, or text-to-speech, is the conversion of text input into human-like speech. Although on the surface the concept may seem simple, the complexity of making a sound humanlike requires vast amounts of AI training. DeepMind has developed groundbreaking technology called WaveNet that can create extremely human-sounding voices. Combining this with neural networks yields an increasing range of voices and options.

SOME KEY FEATURES OF SPEECH SYNTHESIS

Denne historien er fra April 2020-utgaven av NET.

Start din 7-dagers gratis prøveperiode på Magzter GOLD for å få tilgang til tusenvis av utvalgte premiumhistorier og 9000+ magasiner og aviser.

Denne historien er fra April 2020-utgaven av NET.

Start din 7-dagers gratis prøveperiode på Magzter GOLD for å få tilgang til tusenvis av utvalgte premiumhistorier og 9000+ magasiner og aviser.

FLERE HISTORIER FRA NETSe alt
Camille Gribbons
NET

Camille Gribbons

UX designer at Booking.com, Camille Gribbons reveals how she first got into the industry

time-read
7 mins  |
June 2020
THE 5G UI REVOLUTION
NET

THE 5G UI REVOLUTION

Tris Tolliday describes his vision of a web UI catapulted forwards by 5G

time-read
3 mins  |
June 2020
HOW TO SHOWCASE YOUR DEV SKILLS
NET

HOW TO SHOWCASE YOUR DEV SKILLS

Aude Barral shares 5 top tips for landing your dream developer job

time-read
3 mins  |
June 2020
KNIVES OUT
NET

KNIVES OUT

Murder mystery film, Knives Out, grabbed everyone’s attention, and so did the fun website that promoted it. Oblio tells Tom May how it created its innovative 3D navigation

time-read
6 mins  |
June 2020
HOW EMOTIONAL LABOUR HINDERS WOMEN IN TECH
NET

HOW EMOTIONAL LABOUR HINDERS WOMEN IN TECH

Christine Brewis, head of digital marketing at Studio Graphene, discusses how gender parity in tech has changed over the last ten years, and what more can be done

time-read
5 mins  |
June 2020
EDAN KWAN
NET

EDAN KWAN

He swapped life as a singer for a career making eye-popping digital visuals. The Lusion founder chats to Tom May about battling demons, winning awards and where digital advertising is heading

time-read
8 mins  |
June 2020
ANDREW COULDWELL
NET

ANDREW COULDWELL

The Brit in LA discusses his new book on design systems, Laying the Foundations

time-read
3 mins  |
June 2020
Top 5 Tips For Ensuring Web Content Is Accessible For All
NET

Top 5 Tips For Ensuring Web Content Is Accessible For All

Merlyn Meredith outlines five top tips for ensuring web content is accessible for all

time-read
2 mins  |
May 2020
WHAT DOES THE FUTURE HOLD FOR BROWSERS?
NET

WHAT DOES THE FUTURE HOLD FOR BROWSERS?

Nico Turco examines the state of play with browsers, whether developers should encourage diversity or monopoly and how Google fits into it all

time-read
6 mins  |
May 2020
YEARS IN THE MAKING
NET

YEARS IN THE MAKING

Exclusively for net: The latest in a series of anonymous accounts of nightmare clients

time-read
3 mins  |
May 2020