Nodes/comfyui-timesaver/TS Silero TTS
ComfyUI Node

TS Silero TTS

Silero TTS v5_3_ru with ComfyUI AUDIO output.

By AlexYez·Created 2 years ago·Updated 3 days ago· 11
TS Silero TTS
    • audio
    text
    input_formattext
    speakerxenia
    run_devicegpu
    enable_chunkingtrue
    max_chunk_chars900
    chunk_pause_ms120
    put_accenttrue
    put_yotrue
    put_stress_homotrue
    put_yo_homotrue
    CategoryTS/Audio

    Inputs (11)

    NameTypeDefaultDescription
    textSTRINGText or SSML content for speech synthesis.
    input_formatCOMBOtextInput mode: plain text or SSML.
    speakerCOMBOxeniaSilero speaker voice.
    run_deviceCOMBOgpuExecution device for Silero model.
    enable_chunkingBOOLEANtrueAutomatically split long text into chunks to avoid Silero length limits.
    max_chunk_charsINT900200–4000Approximate maximum characters per chunk.
    chunk_pause_msINT1200–3000Silence between generated chunks in milliseconds.
    put_accentBOOLEANtrueAdd stress marks to common words where user did not provide them.
    put_yoBOOLEANtrueReplace e with yo where needed.
    put_stress_homoBOOLEANtrueAdd stress marks for homographs without yo.
    put_yo_homoBOOLEANtrueAdd stress marks for homographs with yo.

    Outputs (1)

    NameTypeDescription
    audioAUDIOSynthesized speech audio.