Nodes/ComfyUI-API-Toolkit/ElevenLabs - Text to Speech
ComfyUI Node

ElevenLabs - Text to Speech

A ComfyUI node in API Toolkit/ElevenLabs/TTS with 17 inputs and 2 outputs.

By IxMxAMAR·Created 5 months ago·Updated about a month ago· 1
ElevenLabs - Text to Speech
    • audio
    • raw_response_info
    api_key
    text
    voice_id
    modeleleven_v3
    stability0.50
    similarity_boost0.75
    style0.00
    speed1.00
    use_speaker_boosttrue
    languageAuto Detect
    apply_text_normalizationauto
    output_formatmp3_44100_128
    seed0
    previous_text
    next_text
    use_pvc_as_ivcfalse
    pronunciation_dictionary_locators
    CategoryAPI Toolkit/ElevenLabs/TTS

    Inputs (17)

    NameTypeDefaultDescription
    api_keySTRING
    textSTRINGText to convert to speech. Supports v3 audio tags like [whispers], [laughs], [excited].
    voice_idSTRINGVoice ID. Connect from Voice Selector or Fetch Voices node.
    modelCOMBOeleven_v38 options: eleven_v3, eleven_multilingual_v2, eleven_flash_v2_5, eleven_turbo_v2_5, eleven_flash_v2, eleven_turbo_v2, +2
    stabilityoptFLOAT0.500–1Voice stability. Lower = more expressive/emotional, Higher = more consistent/monotone. Creative(<0.5), Natural(0.5), Robust(>0.5).
    similarity_boostoptFLOAT0.750–1How closely AI adheres to the original voice. Too high may introduce artifacts.
    styleoptFLOAT0.000–1Style exaggeration. Increases expressiveness but reduces stability. Recommended: 0 for most use cases.
    speedoptFLOAT1.000.5–2Speech speed. 1.0 = normal, <1.0 = slower, >1.0 = faster.
    use_speaker_boostoptBOOLEANtrueBoost similarity to original speaker. Increases latency slightly.
    languageoptCOMBOAuto DetectLanguage for the model. Auto Detect lets the model decide.
    apply_text_normalizationoptCOMBOautoText normalization: 'auto' = model decides, 'on' = always normalize, 'off' = skip.
    output_formatoptCOMBOmp3_44100_128Audio output format. mp3_44100_192 and opus require Creator tier+.
    seedoptINT00–4294967295Seed for reproducibility. 0 = random. Determinism not guaranteed.
    previous_textoptSTRINGText that came BEFORE this segment. Helps maintain natural flow across chunks.
    next_textoptSTRINGText that comes AFTER this segment. Helps the model anticipate pacing.
    use_pvc_as_ivcoptBOOLEANfalseUse IVC version of a Professional Voice Clone.
    pronunciation_dictionary_locatorsoptSTRINGJSON array of {"pronunciation_dictionary_id": ..., "version_id": ...} objects.

    Outputs (2)

    NameTypeDescription
    audioAUDIO
    raw_response_infoSTRING