Skip to content
KugelAudioDocs

Models

KugelAudio models: the current Kugel 3.5 and Kugel 3 text-to-speech models, Clarity 1 for speech enhancement, what each supports, and the legacy model IDs.

On this page

KugelAudio exposes Kugel 3 and Kugel 3.5 as its text-to-speech models and Clarity 1 for speech enhancement.

Kugel Ear 1 transcribes speech to text.

Kugel Fluid 1 holds live voice conversations.

Both hosted regions serve the models, default and legacy IDs on this page. An on-premise deployment serves only the models it was installed with; call /v1/models on it to see which.

Current models

Model IDNameBest for
kugel-3.5Kugel 3.5Voice agents and phone conversations. Our newest model, built on Kugel 3 and trained to say short replies, timed pauses and spelled-out codes more reliably. The default when you send no model_id.
kugel-3Kugel 3Voice agents, narration, brand voices, streaming, and multilingual TTS. The previous default; send model_id kugel-3 to keep using it.
clarity-1Clarity 1Speech enhancement: removing background noise from speech, or keeping one speaker's voice and removing every other voice and sound, for recordings or live audio. See Speech enhancement.

Speech to text

Model IDNameBest for
kugel-ear-1Kugel Ear 1Speech to text in ten languages, for recordings or live calls: transcribes the language you name or detects it, lists spelling alternatives for uncertain words such as names, ends turns with KugelTurn, and spells your vocabulary your way. See Speech to text.

Speech to speech

Model IDNameBest for
fluid-1Kugel Fluid 1Live voice conversations over one WebSocket, with your own backend answering what the agent cannot. Works with the official OpenAI Python SDK. See Speech to speech.

Legacy model IDs

kugel-2.5, kugel-2-turbo, kugel-2, kugel-1, and kugel-1-turbo are aliases that run on kugel-3.5. A request is billed at the rate of the ID you sent, not at the kugel-3.5 rate: kugel-2-turbo is charged the Turbo rate. Usage and billing show the ID you sent. kugel-1 and kugel-1-turbo keep their 5,000-character input limit. Use kugel-3.5 or kugel-3 in new integrations.

Example

Python
audio = client.tts.generate(
    text='Welcome to KugelAudio. <break time="400ms"/> How can I help you today?',
    model_id="kugel-3.5",
    voice_id=1071,
    cfg_scale=2.0,
)

Capabilities

Capabilitykugel-3
Voice cloning (zero-shot)Supported
IPA custom pronunciationSupported
Built-in text normalizationSupported
Input text streamingSupported
Output audio streamingSupported
Word-level timestampsSupported
Multilingual TTS39 languages, single multilingual model
Break tags (break element)Supported
Sample rate24 kHz native; 8 kHz, 16 kHz, 22.05 kHz, 24 kHz, and 44.1 kHz output options
Max input length10,000 characters

kugel-3.5 runs with the same engine settings as kugel-3: input and output streaming, built-in text normalization, break tags, the same output sample rates, and the 10,000-character input limit. It is served in the EU and US regions. Your plan can set a lower per-request limit; see pricing.

Listing models

GET /v1/models returns the current models only; legacy IDs are accepted but not listed. See the /v1/models reference.

Next steps