Shogo Ando

Hello everyone.

Introducing a tool that allows you to upload audio files or audio contained in video files, use speech recognition on the AmiVoice Cloud Platform, and easily create subtitle files.UDトークIt was developed and released by Shamrock Records, Inc., a developer of a communication support and conversation visualization app.

AmiVoice Cloud Platform's functions alone cannot perform voice recognition on video files, but this tool can. It also has features for creating subtitles, such as cue playback, so it's recommended for those who want to create subtitles.

The tool is here.

Subtitle Editor for Files – UD Talk Tools

You can edit UD Talk logs (.csv) and subtitle files (.srt) while playing locally stored video or audio files.

tools.udtalk.jp

Detailed instructions on how to use it are explained on Shamrock Records' YouTube channel.

Shortly after the tool was released, it also supported video files.

As explained in the video, to use this tool you will need to register as an AmiVoice Cloud Platform user. Detailed instructions are also explained in this article.

Try AmiVoice Cloud Platform

AmiVoice Cloud Platform-Tech Blog

The source code has been made public as open source for the sake of transparency. The key point is that the audio is extracted in the browser without sending the video file to a server, so there is no risk of someone seeing the video (however, please note that audio data is sent to AmiVoice's server during voice recognition). If you would like to use this as reference for developing voice recognition applications, please take a look.

GitHub – ShamrockRecords/tools

Contribute to ShamrockRecords/tools development by creating an account on GitHub.

github.com