audio
Reference for the audio tool of AI Audio: create, runs, list, get, delete, usage and providers, with every action.
Sound from words in a workspace. A run you queue through the door is made as soon as somebody in that workspace has AI Audio open, because the Preview provider runs in a browser. Server providers run on their own once their keys are set.
Call it as geenius_geeniusaudio(tool: "audio", action: "<action>", args: {...}) through Geenius OS.
Actions#
| Action | What it does |
|---|---|
create | Queues a run of 1 to 4 takes of a sound and answers the run's id, the credits it costs and the app address. Speech: what to say. Dialogue: a script, one line per turn as "Ava: ..." with exactly two speakers. Music or effect: a description. Language, voice, speed (0.5 to 2), emotion, mood, seconds and loop depend on the kind. Premium and Max only. |
runs | The latest runs with their state (queued, running, done or failed) and takes. |
list | Sounds; a query searches words in the prompt. |
get | One sound with its file address, length and waveform. |
delete | A run and its takes for good; confirm with the run id. |
usage | Credits used this month against the plan, and whether the plan can make sound. |
providers | The models, what each can do and whether it is ready here. |