Text-to-Speech with SSML
What is SSML and how do the buttons work?
SSML (Speech Synthesis Markup Language) is a special markup language that allows you to influence how text is read aloud by the artificial voice. For example, you can insert pauses, switch voices, or emphasize certain words.
Here's a description: SSML Button Description
Activate marking mode to specifically select words. Click on one or more words, then use a function button to perform the desired action on the highlighted text.
Explanation of each SSML button
- 🎤 Voice: Temporarily changes the voice to read individual words or sentences with a different voice.
- ⏸️ Break: Inserts a break after the selected word to naturally adjust the reading speed.
- 🎛️ Prosody: Changes the speaking rate, pitch, or volume of the selected text for a more dynamic reading experience.
- 💬 Say-as: Determines how text is interpreted, e.g., as a date, time, or number.
- 🔄 Substitution: Replaces the selected word with another during playback, without altering the original text.
- 🔊 Audio: Allows inserting external audio files (e.g., sound effects) directly into the text flow.
- ✨ Emphasis: Highlights important words or sentences through increased or reduced emphasis.
- 🎵 Pitch: Adjusts the pitch to create emotional effects or special accents.
- 🔈 Volume: Passt die Lautstärke an, um bestimmte Textstellen hervorzuheben oder zu dämpfen.
- 😊 Cheerful (Google Style): Reads the text cheerfully and vividly.
- 💬 Conversational (Google Style): Gives the text a natural, conversational emphasis.
- 📰 News (Google Style): Reads the text in a typical newscaster style.
Lade Credits...
