Skip to main content

//clika-runtime/io.clika.modelverse/VoiceReference

VoiceReference

sealed interface VoiceReference

The voice a text-to-speech request clones: a clip of the speaker, mono, a few seconds long (a voice-cloning family reads about the first ten seconds for the generator and the whole clip, silence trimmed, for the speaker embedding). Any sample rate; the library resamples.

Inheritors​

Pcm16
File

Types​

NameSummary
File[common]
class File(val path: String) : VoiceReference
An audio file on disk, in any format the library decodes (WAV, FLAC, MP3, ...).
Pcm16[common]
class Pcm16(val samples: ShortArray, val sampleRate: Int) : VoiceReference
16-bit mono samples at sampleRate hertz. Needs TtsLoadOptions.scratchDir.