SpokenData is an automatic transcription service based on Speech to Text technology. As a registered user you get a personalized media library with tagging and categories. You can add new media files by using an upload form or by passing a link. Each new media file is processed depending on your settings. You can select from automatic speech recognition in several languages, voice activity detection, speaker segmentation or text to audio alignment. The generated transcription can be modified in the online subtitles editor.
A REST API is also available. The API allows developers to integrate SpokenData into desktop, mobile or web applications. As an example, SpokenData API enables developers to add a new audio/video file to their accounts and directly download its speech transcription in various formats such as XML, SRT, TXT or plain text.
Features
Input file formats: almost any audio or video file and YouTube videos
Output transcription formats: SRT, TXT or XML
Language Coverage
English
(Latin),
Russian
(Cyrillic),
Chinese
,
Spanish; Castilian
(Latin),
Czech
(Latin),
Slovak
(Latin)