Voice Preview
adminHow this works
Load a voice from the repo or start a new one, generate takes for each filler and stage the one that you like, then download the zip and attach it to the task.
1Voice which one, who it is, how it sounds
2Fillers one row per phrase — generate, compare, stage
| Phrase ships in config.json | Say as spoken instead | Takes pick the one that you like |
|---|
3Notes
Kept in voice.md above the generated filler tables, and round-tripped
verbatim. Task, tuning notes, anything the next person needs.
4Review what ships, and what is wrong with it
How this works
Hear any voice say a line the way a caller would, at 8 kHz: one from the repo, a Gemini preset or library voice, or one you design or clone here. Nothing here edits a voice — Save as new voice starts one on the Voices tab.
How this works
Every voice the Google project stores, designed or cloned, made here or anywhere else, and what uses it. They all count toward the project's cap. A voice nothing ships can be deleted; one the repo or the open session uses can't.
| Name | Type | Id | Used by |
|---|