Gandr for game studios.
0.1-1.2
prosody dial, continuous, per request
A cast of forty is forty ten-second clips with no per-voice fee, one continuous prosody dial per request, and seeds so a rebuilt dialogue bank does not silently change a line a player has already heard. Your script is enormous and mostly unheard: barks, reactive lines, the conversation behind a door most players never open.
The lines that never get recorded
Which lines exist is decided by what it costs to voice them. A guard who says one of three things is cheap; a guard who reacts to the hour, the weather and whether you have been here before is a session nobody booked.
Directing a performance from the request
- One continuous prosody dial per request, so one character can read tired, clipped or wide-open without recasting, and a held seed makes a take repeatable.
- Five prosody dials, including melodic range, continuous across its span.
- Seeds, so a rebuilt dialogue bank does not silently change lines a player has already heard.
Notes
Can one voice cover a whole cast?
No, and it should not. Each character wants its own reference clip, cloning is instant and carries no per-voice fee, so a cast of forty is forty clips rather than forty contracts.
Can dialogue be generated at runtime?
Yes, over a WebSocket, with the first chunk arriving while the rest renders. A baked bank uses the bytes endpoint instead.
A key and one stream to size it on, before anyone talks about a fleet.
Get a key for your stack