ComfyUI Node
ElevenLabs Pro - Text to Dialogue with Timestamps
A ComfyUI node in ElevenLabs Pro/TTS with 32 inputs and 3 outputs.
ElevenLabs Pro - Text to Dialogue with Timestamps
- audio
- timestamps_json
- voice_segments_json
◄api_key►
◄text1►
◄voice_id1►
◄modeleleven_v3►
◄text2►
◄voice_id2►
◄text3►
◄voice_id3►
◄text4►
◄voice_id4►
◄text5►
◄voice_id5►
◄text6►
◄voice_id6►
◄text7►
◄voice_id7►
◄text8►
◄voice_id8►
◄text9►
◄voice_id9►
◄text10►
◄voice_id10►
◄stability0.50►
◄apply_text_normalizationoff►
◄languageAuto Detect►
◄output_formatmp3_44100_192►
◄seed0►
◄enable_loggingtrue►
◄previous_text►
◄future_text►
◄use_pvc_as_ivcfalse►
◄pronunciation_dictionary_locators►
CategoryElevenLabs Pro/TTS
Inputs (32)
| Name | Type | Default | Description |
|---|---|---|---|
| api_key | STRING | — | |
| text1 | STRING | Speaker 1 text. | |
| voice_id1 | STRING | Speaker 1 voice ID. | |
| model | COMBO | eleven_v3 | 2 options: eleven_v3, eleven_v4 |
| text2opt | STRING | — | |
| voice_id2opt | STRING | — | |
| text3opt | STRING | — | |
| voice_id3opt | STRING | — | |
| text4opt | STRING | — | |
| voice_id4opt | STRING | — | |
| text5opt | STRING | — | |
| voice_id5opt | STRING | — | |
| text6opt | STRING | — | |
| voice_id6opt | STRING | — | |
| text7opt | STRING | — | |
| voice_id7opt | STRING | — | |
| text8opt | STRING | — | |
| voice_id8opt | STRING | — | |
| text9opt | STRING | — | |
| voice_id9opt | STRING | — | |
| text10opt | STRING | — | |
| voice_id10opt | STRING | — | |
| stabilityopt | FLOAT | 0.500–1 | Voice stability. Lower = more expressive/emotional, Higher = more consistent/monotone. Creative(<0.5), Natural(0.5), Robust(>0.5). |
| apply_text_normalizationopt | COMBO | off | eleven_v3 requires 'off' — keeping default. |
| languageopt | COMBO | Auto Detect | 33 options: Auto Detect, English (en), Arabic (ar), Bulgarian (bg), Chinese (zh), Croatian (hr), +27 |
| output_formatopt | COMBO | mp3_44100_192 | Audio output format. mp3_44100_192 and opus require Creator tier+. |
| seedopt | INT | 00–4294967295 | Seed for reproducibility. 0 = random. Determinism not guaranteed. |
| enable_loggingopt | BOOLEAN | true | If False, requests zero-retention mode (audio + text not stored by ElevenLabs). Required for HIPAA / privacy-sensitive content. |
| previous_textopt | STRING | Context only — up to 100 characters that come right BEFORE this dialogue, for continuity. Not supported by every model. | |
| future_textopt | STRING | Context only — up to 100 characters that come right AFTER this dialogue, for continuity. Not supported by every model. | |
| use_pvc_as_ivcopt | BOOLEAN | false | Use the IVC version of a Professional Voice Clone. |
| pronunciation_dictionary_locatorsopt | STRING | JSON array of {"pronunciation_dictionary_id": ..., "version_id": ...} objects (up to 3). |
Outputs (3)
| Name | Type | Description |
|---|---|---|
| audio | AUDIO | — |
| timestamps_json | STRING | — |
| voice_segments_json | STRING | — |