MiniMax text to speech
MiniMax turns each response into a performed line.
Playworlds uses MiniMax text-to-speech for spoken game-master narration and AI companion dialogue. The default production configuration uses Speech 2.8 HD with separate voice identities for each role.
Play PlayworldsVoice or text · AI game master · Persistent saves
What it does
One focused layer in a multi-model game system.
- Default model
- speech-2.8-hd
- Job in Playworlds
- Narration and character speech
- Output
- Rendered spoken performance
Why the layer matters
Designed around the rhythm of play.
Role-aware voices
The game master and teammate use separate voice IDs so players can hear who is speaking before reading a label.
Conversation pacing
Responses are segmented into playable lines, reducing the wait between a decision and the first spoken reaction.
Natural interruption
The conversation can recover gracefully when a player speaks over a response or changes direction.
Common questions
The short version
What does MiniMax Speech 2.8 HD do in Playworlds?
MiniMax Speech 2.8 HD provides text to speech as one part of the Playworlds voice-adventure stack.
Is Playworlds built around a single AI model?
No. Playworlds separates narrative reasoning, speech recognition, text-to-speech, voice activity detection, and persistent game state into distinct layers.