Text to speech Gradium
Phonon 31M En
Phonon 31M - English streaming TTS from Gradium (24 kHz, 38 built-in voices), one GGUF for the zzz CPU engine
phonon-31m-en Make it part of your app.
One model. Your language.
use xybrid::ModelLoader;
use xybrid::ir::{Envelope, EnvelopeKind};
// Load the TTS model
let model = ModelLoader::from_registry("phonon-31m-en").load()?;
// Generate speech from text
let input = Envelope::new(EnvelopeKind::Text("Hello from Xybrid!".into()));
let result = model.run(&input, None)?;
// result.audio_bytes() holds the speech, as raw PCMBuilt with Xybrid Quickstart
Available variants
| Variant | Format | Quantization | Size |
|---|---|---|---|
| android-arm64DEFAULT | GGUF | q8_0 | 71.0 MB |
| linux-x86_64 | GGUF | q8_0 | 71.0 MB |
| macos-arm64 | GGUF | q8_0 | 71.0 MB |