generate_to_file()

Synthesize speech from text and save the audio directly to a file.

Signature

KittenTTS.generate_to_file(
    text,
    output_path,
    voice="expr-voice-5-m",
    speed=1.0,
    sample_rate=24000,
) -> None

This is a convenience wrapper around generate() that writes the resulting audio to disk using soundfile. Use it when you don’t need to manipulate the audio array in memory.

Parameters

text · str · required

The input text to synthesize.

output_path · str · required

File path where the audio will be saved. The file format is inferred from the extension.

Supported formats: .wav, .flac, .ogg.

voice · str · default: "\"expr-voice-5-m\""

Voice to use for synthesis. Accepts any friendly name from available_voices: Bella, Jasper, Luna, Bruno, Rosie, Hugo, Kiki, Leo.

The default "expr-voice-5-m" is the internal ID for Leo. You can pass either the friendly name or the internal ID.

speed · float · default: "1.0"

Speech speed multiplier.

• 1.0 — normal speed
• Values below 1.0 slow down speech
• Values above 1.0 speed it up

sample_rate · int · default: "24000"

Audio sample rate in Hz. The model produces audio at 24 kHz. Change this only if you need to resample the output for a specific downstream use case.

Use generate_to_file() when you only need the saved file and don’t need to manipulate the audio array in your code. It is equivalent to calling generate() and then soundfile.write().

Usage examples

Save as WAV

from kittentts import KittenTTS

tts = KittenTTS()
tts.generate_to_file(
    "Hello, this is KittenTTS.",
    "output.wav",
)