Interface: LmntSpeechModelSettings
Hierarchy
-
↳
LmntSpeechModelSettings
Properties
api
• Optional api: ApiConfiguration
Defined in
packages/modelfusion/src/model-provider/lmnt/LmntSpeechModel.ts:20
length
• Optional length: number
Produce speech of this length in seconds; maximum 300.0 (5 minutes)
Defined in
packages/modelfusion/src/model-provider/lmnt/LmntSpeechModel.ts:40
observers
• Optional observers: FunctionObserver[]
Observers that are called when the model is used in run functions.
Inherited from
SpeechGenerationModelSettings.observers
Defined in
packages/modelfusion/src/model-function/Model.ts:8
seed
• Optional seed: number
Seed used to specify a different take; defaults to random
Defined in
packages/modelfusion/src/model-provider/lmnt/LmntSpeechModel.ts:35
speed
• Optional speed: number
The talking speed of the generated speech. A Floating point value between 0.25 (slow) and 2.0 (fast); defaults to 1.0
Defined in
packages/modelfusion/src/model-provider/lmnt/LmntSpeechModel.ts:30
voice
• voice: string
The voice id of the voice to use for synthesis.
Defined in
packages/modelfusion/src/model-provider/lmnt/LmntSpeechModel.ts:25