ComfyUI Node: F5-TTS Audio advanced

Authored by niknah

Created

Updated

223 stars

Category

audio

Inputs

sample
    speech STRING
    seed INT
    model
    • F5v1
    • F5
    • F5-DE
    • F5-ES
    • F5-FR
    • F5-HI
    • F5-IT
    • F5-JP
    • F5-TH
    • E2
    vocoder
    • auto
    • vocos
    • bigvgan
    speed FLOAT
    model_type
    • E2TTS_Base
    • F5TTS_Small
    • F5TTS_Base
    • F5TTS_v1_Base
    • E2TTS_Small
    sample_audio AUDIO
    sample_text STRING
    target_rms FLOAT
    cross_fade_duration FLOAT
    nfe_step INT
    cfg_strength FLOAT
    sway_sampling_coef FLOAT
    speed_type
    • torch-time-stretch
    • F5TTS
    • TDHS
    fix_duration FLOAT

    Outputs

    AUDIO

    Extension: ComfyUI F5-TTS

    Text to speech with F5-TTS

    Authored by niknah

    View Nodes

    Run ComfyUI workflows in the Cloud!

    No downloads or installs are required. Pay only for active GPU usage, not idle time. No complex setups and dependency issues

    Learn more