kugelaudio

kugelaudio

Runs on one key, KUGELAUDIO_API_KEY.

import { kugelaudio } from "curb/providers";

kugelaudio.llm(options?: KugelaudioLlmOptions): LlmDescriptor;
kugelaudio.stt(options?: KugelaudioSttOptions): SttDescriptor;
kugelaudio.tts(options?: KugelaudioTtsOptions): TtsDescriptor;

kugelaudio.llm(options?)

KugelAudio’s EU-hosted LLM, in closed alpha.

OptionTypeDefault
modelone of KUGELAUDIO_LLM_MODELSDEFAULT_KUGELAUDIO_LLM_MODEL

kugelaudio.stt(options?)

Kugel Ear 1.

OptionTypeDefaultWhat it does
languagestringdetects German or English"de", or "de,fr" to detect among several, expecting the first. Supported: de, en, fr, it, es, pt, nl, pl, ro
turnDetection"kugelturn", "vad""kugelturn"What ends a caller’s turn: KugelTurn hears when the speaker finished; vad waits for a second of pause
turnDetectionLevel"responsive", "conservative""responsive"conservative holds longer through a pause mid-thought
boostedPhrasesstring[]Names and terms to spell the way you write them (Pronunciation)
dictionaryIdsnumber[]every active dictionaryDictionaries used as vocabulary; [] for none
projectIdnumberthe key’s projectThe project whose dictionaries apply

kugelaudio.tts(options?)

OptionTypeDefaultWhat it does
voicenumberthe voice of languageA KugelAudio voice id
modelstring"kugel-3.5"The TTS model
languagestring"en"How text is read, and which voice reads it when voice is not set
dictionaryIdsnumber[]Pronunciation dictionaries. Needs projectId
projectIdnumberThe number in your dashboard URL

Example

<Agent llm={kugelaudio.llm()} stt={kugelaudio.stt({ language: "de" })} tts={kugelaudio.tts({ language: "de" })} />

Version history

VersionChanges
v1.11.9kugelaudio.llm() added
v1.4.33kugelaudio.stt() added
v1.2.6kugelaudio.tts() introduced