Text to speech - required information
Available solutions
- Manual file generation through the platform interface.
- Text-to-speech generation via API (integration and automation on the Partner's side).
This is a stable method where the Partner, after gaining access to text-to-speech and the API, must integrate this functionality with their CMS. The process involves sending the article text via API and receiving a SID code for the audio content, which must be placed in the player embed code.
More details can be found in point 27 "Command 'addSpeech'" on the page: API Documentation. - Text-to-speech generation via automatic text detection by our script.
After a preliminary analysis of the structure of the given site, we prepare a special embed code that automatically detects the article text on the page and sends it to our system during the user's first visit. Then, within about a minute, a text-to-speech file is generated. This file automatically appears on the page in the player and will be available to all subsequent users. The same embed code can be used on any subpage where a text-to-speech file needs to be generated.
Technical arrangements
For all solutions (1, 2, 3):
- Placement of the text-to-speech player on the website.
- Appearance of the player on mobile and desktop: Please choose from the examples below or provide your own HTML template.
- Where the ad should be displayed in the case of video ads (main player and miniature).
Additional arrangements for solution 2 (API):
- Estimated number of new articles per day.
- Average number of characters in an article.
- Are the articles edited after publication and how often?
Additional arrangements for solution 3 (Automatic script):
- Estimated number of new articles per day.
- Average number of characters in an article.
- Are the articles edited after publication and how often?
- How is the information about article creation and its last modification stored on the site (e.g., datePublished, dateModified).
- Choosing the default voice: List of available voices