Say it out loud
Say words out loud to the person in a natural voice (their own cloned voice or a neutral one), made once by one of their own devices and kept in their files so every device of theirs plays it
Runs in the person's account and places the speaking on the first of their awake devices that keeps a speech model (src/placement.json job speak, such as tool:speak-on-this-mac on their Mac), which makes the sound in the voice of the place it is said in (the person's own list rows, tool:voice-for), else their chosen voice, and keeps it in their files under /Voice/Said at its natural pace. Answers { file, name, seconds, voice, engine, produced_by, made_on, speed }: whoever plays it plays it at speed with the pitch kept. Trillion never pays for a voice: with no such device awake it answers system_voice true with the words, and the device the person is at says them with its own voice.
What it asks for
- text (Needed, words): The words to say
- voice (Optional, words): A voice id of the person's (a row of their Voices list, tool:voice-for); the place's voice, else their chosen voice, when left out
- place (Optional, words): Where this is said: a row id of the person's list of places Trillion speaks (tool:voice-for lists them, such as said-out-loud, calls, voice-messages, podcasts, posts, car, coaching), whose voice and speed it uses
Use it from your AI
Connect the AI you already use to Trillion once. Then ask in your own words; your AI finds this tool by what it does and runs it.
Say to your AI: “Use Trillion to say words out loud to the person in a natural voice (their own cloned voice or a neutral one), made once by one of their own devices and kept in their files so every device of theirs plays it”
What your AI calls: run_tool {"tool_id":"tool:speak"}