AItalk webAPI
Speech synthesis API
AItalk webAPI

Ideal for WEB services! Utilizes a handy yet high-quality speech synthesis

A service that can utilize high-quality speech synthesis engine AITalk® in SaaS format from WEB services. There’s no need to develop and apply the server for speech synthesis on your own, and you can easily start the service utilizing speech synthesis in various services such as web service, smart phone apps, and campaigns. It can also express emotions (*) which realized recitation in rich expressions of emotions that surpass your monotonous image of speech synthesis.
*Speakers who correspond to emotion include Nozomi (Joy, Anger, and Sadness), Maki (Joy, Anger, and Sadness), Reina (Joy), Taichi (Joy) only.

AItalk webAPI

AITalk® WebAPI is recommended for people who

Wants to start the service using the speech synthesis while minimizing the cost for development and applications.

No need to develop or operate speech synthesis server. It’s all on us. Save resources for application because you don’t have to develop and apply on your own.

Wants to deploy the service using speech synthesis in multi-devices.

It takes tremendous effort to integrate the speech synthesis engines into Android, iOS, WindowsCE, Windows, Mac, and etc. AITalk® WebAPI enables easy support for multi-devices.

Characteristics of AITalk®WebAPI


Ability of expressing emotions (*)

We realized expressions of emotions suitable for each situation and use.
*Speakers who correspond to emotion include Nozomi (Joy, Anger, and Sadness), Maki (Joy, Anger, and Sadness), Reina (Joy), Taichi (Joy) only.

 


Natural voices almost as if they sound like actual humans

AITalk®WebAPI realized natural, human-like voice unlike the previous robotic speech synthesis.

 


A spectacular variety of speakers

We have 15 standard speakers and 2 Kansai dialect speakers, in total of 17 speakers. You may use for various purposes.

Demonstration

Main Functions for AITalk® WebAPI


Emotion adjustment function (*)

*Speakers who correspond to emotion include Nozomi (Joy, Anger, and Sadness), Maki (Joy, Anger, and Sadness), Reina (Joy), Taichi (Joy) only.


Text speech synthesis conversion


Speed adjustment


Pitch adjustment function


Word dictionary function


Volume adjustment


Selecting a speaker

* Word dictionary function is not available for Kansai-dialect speaker. We thank you for your understanding.

AITalk® WebAPI Application Examples


Web campaign

– To plan unique and fun Web campaigns

– To carry out user-interactive campaigns using voices of celebrities and voice actors

<If you use AITalk® WebAPI×CustomVoice…>

– You can use the campaign tricks that reiterate the user’s input text into a voice of a selected person.


News reiteration application

– To deliver a real-time reiteration service for up-to-date news without having to record.
– To develop an app in which users can listen to the news in a self-picked voice.

<If you use AITalk® WebAPI…>

– It can reiterate the news in real-time without having a news presenter to read.
– You may choose from 4 men, 7 women, and 4 children, in total 15 speakers of your choice.


Voice dialogue

– To easily use speech synthesis while keeping the initial development and application cost low.
– To develop an app that realizes conversations with various characters.

<If you use AITalk® WebAPI×CustomVoice…>

– You can start a speech synthesis service while saving the initial development and application costs, such as server maintenance and monitoring costs.
– CustomVoice allows you to create an application that can converse in an original character voice.
*Voice dialogue requires additional system of voice identification and intention interpretation.


Interactive Voice Response (IVR)

– To make AI automatically respond to variable information.
– To use speech synthesis in interactive voice response while saving the initial and application cost.

<If you use AITalk® WebAPI…>

– Responding to variable information in real-time becomes possible without having an operator to respond.
– You can affiliate with IVR to create speech synthesis while saving initial development and application costs, such as server maintenance and monitoring costs.