Skip to main content
Audio models are selected on the audio-generating nodes. They cover three jobs: turning text into speech, composing music from a description, and adding sound effects to a video.

Families

ModelProviderUsed byJob
ElevenLabs Multilingual v2ElevenLabsGenerate SpeechText-to-speech
ElevenLabs v3ElevenLabsGenerate SpeechText-to-speech
ElevenLabs Music v1ElevenLabsGenerate MusicMusic generation
Mirelo 1.5FALAdd Sound EffectsVideo sound effects

Settings

Each audio node exposes the settings relevant to its model. Availability depends on the model you pick.

Speech

SettingWhat it does
stabilityVoice consistency, from 0 to 1. Higher values give a steadier delivery.
similarity_boostHow closely the output matches the chosen voice, from 0 to 1.
styleStyle exaggeration, from 0 to 1.
speedPlayback speed, from 0.5 to 2.

Music

SettingWhat it does
durationTrack length in seconds, from 3 to 600.
force_instrumentalGenerate an instrumental track with no vocals.
See Model settings for the full reference.

Generate Speech

Convert text to spoken audio with an ElevenLabs voice.

Generate Music

Compose a music track from a text description.

Add Sound Effects

Generate and attach sound effects to a video.