Speech
@kortexya/reasoninglayer / Speech
Speech
Section titled “Speech”Speech — voice cloning, synthesis, transcription, and speech sessions.
Covers the /api/v1/speech/* endpoints: enrolling a cloned voice from a
reference clip, listing engines and voices, opening a duplex speech
session, synthesizing speech to raw audio bytes, and transcribing a
short utterance.
References
Section titled “References”EnrollVoiceRequest
Section titled “EnrollVoiceRequest”Re-exports EnrollVoiceRequest
ListEnginesResponse
Section titled “ListEnginesResponse”Re-exports ListEnginesResponse
ListVoicesResponse
Section titled “ListVoicesResponse”Re-exports ListVoicesResponse
OpenSpeechSessionRequest
Section titled “OpenSpeechSessionRequest”Re-exports OpenSpeechSessionRequest
OpenSpeechSessionResponse
Section titled “OpenSpeechSessionResponse”Re-exports OpenSpeechSessionResponse
SpeechEngine
Section titled “SpeechEngine”Re-exports SpeechEngine
SpeechErrorCode
Section titled “SpeechErrorCode”Re-exports SpeechErrorCode
SynthesizeSpeechRequest
Section titled “SynthesizeSpeechRequest”Re-exports SynthesizeSpeechRequest
TranscribeSpeechRequest
Section titled “TranscribeSpeechRequest”Re-exports TranscribeSpeechRequest
TranscribeSpeechResponse
Section titled “TranscribeSpeechResponse”Re-exports TranscribeSpeechResponse
VoiceConsent
Section titled “VoiceConsent”Re-exports VoiceConsent
VoiceProfile
Section titled “VoiceProfile”Re-exports VoiceProfile