What 's OTOROKU

Text-to-Speech System by Tokyo Broadcasting System Television, Inc.

Natural Text-to-Speech
Aligned with Time Codes

Users can easily synthesize voices aligned with time codes by preparing narration scripts with corresponding time codes. 

Support for
Multilingual Contents

With the ability to translate
your script, making your content multilingual becomes a seamless process, allowing it to easily reach audiences worldwide.

Custom Voice Synthesi
(Under Development)

It becomes possible to learn and synthesize the ideal voice tailored
to your content, creating a custom voice that perfectly fits your needs.

VelvetWarm_Na_English.mp4

Create narrations effortlessly and swiftly

By importing narration scripts with time codes, you can effortlessly generate natural synthesized voices synchronized with the time codes. Easily export the audio files and link them seamlessly with your editing software to synchronize with the visuals.

"OTOROKU" is a text-to-speech conversion software developed by TBS-TV and Glowdia (Tokyo Broadcasting System Television) - the Japanese entertainment powerhouse known for the creation of globally popular content/franchises such as "Ninja Warrior/SASUKE" "Takeshi's Castle" and "America's Funniest Videos" which have aired successfully in in multiple languages in over 165 countries/regions.

 

The "OTOROKU" is an intuitive text-to-speech system designed for video editors, offering synthesized voices tailored to the desired audio duration based on provided scripts. Without the need for narrator-led voice recordings, this system enables video editors to engage in more cost-effective, straightforward, and rapid content production.


The term "ROKU" carries the meaning of "sound" in Japanese, while "ROKU" represents the number "6" in Japanese. The pronunciation "ROKU" is a play on words, derived from the Japanese term for recording sound, "録音" (roku-on). Additionally, it echoes the television channel number "6" (TBS) in Japan.