OmniVoice

Diese Soniqo-Seite dokumentiert OmniVoice aus der lokalen speech-swift- / speech-core-Implementierung. Hugging-Face-Bundles sind nach den Integrationshinweisen verlinkt.

Zuerst interne Seite

Landing-Karten und Docs-Menüs führen zuerst hierher; Quellen- und Bundle-Links bleiben auf dieser Seite verfügbar.

Überblick

Modell	OmniVoice
Rolle	Massively multilingual zero-shot voice-cloning TTS
Backend	MLX int8 default bundle; fp16 bundle available
Ausgabe	24 kHz mono waveform
Sprachen	600+ languages
Lizenz	Apache-2.0 upstream family
Status	Programmatic speech-swift runtime used by Studio sidecar
Quelle	k2-fsa OmniVoice
Swift-Produkt	`OmniVoiceTTS`
CLI / Laufzeit	Programmatic runtime; not a primary speech speak engine yet

Verwendung

Das folgende Snippet entspricht der aktuellen API oder dem aktuellen Befehl aus speech-swift.

import OmniVoiceTTS

let model = try await OmniVoiceTTSModel.fromPretrained()
let pcm = try model.generate(
    text: "A new sentence in the reference speaker's voice.",
    referenceAudio: URL(fileURLWithPath: "reference.wav"),
    referenceText: "This is the reference voice.",
    language: "en"
)

Modelllinks

Implementierungsnotizen

Download repairs incomplete caches by checking the backbone, tokenizer files, and audio_tokenizer model before loading.
Generation iteratively unmasks eight acoustic codebooks with classifier-free guidance.
The runtime combines a bidirectional Qwen3 backbone with a Higgs-audio v2 codec encoder/decoder.
Optional instructions cover restricted style controls such as accent, age, gender, pitch, and whisper.