During high-level and detailed design
Starting with sample dialogs for a conversation on Google Home
When you have a clear understanding of the conversational context
Spoken prompts can either be synthesized or recorded speech.
|Synthesized||The Actions on Google platform provides a variety of text-to-speech (TTS) voices that speak different languages. Go to Languages and Locales to hear them. Note that you can adjust the way the synthesized speech sounds by using Speech Synthesis Markup Language (SSML). For example, you may want to add silence or pauses, specify how numbers should be read, or adjust the intonation.|
|Recorded||You can hire a professional voice actor, or even try using your own voice. Either way, you’ll need to record all the audio that will be used in your Action.|
Display prompts have specific formatting requirements.
|Max 640 character limits||There’s a 640 character limit per turn, but we recommend using 300 characters or less.|
|Show your display prompt in 1 or 2 parts||You can have your display prompt show up in 2 parts. Think of this like a carriage return, letting you visually split the display prompt for readability. For example, you might want to split the menu from the question, or separate a joke setup from the punchline.|
|Emojis||Text in a display prompt can include "quotes" and most other unicode characters, including emojis.|