ComfyUI Node
AuK review step X (internal)
Clone each script line independently from the same reference voice, then join the audio in order. Tags request delivery styles; model adherence varies.
AuK review step X (internal)
- model
- encoder
- vae
- reference_audio
- reference_audio_2
- audio
- segment_report
◄script[Happy] Hello there, how are you? (3s)
[Shy][c-whisper] This is our little secret.►
◄words_per_second2.0►
◄gap_seconds0.00►
◄seed0►
◄steps32►
◄guidance2.0►
◄sway-1.00►
◄sound_extra_seconds0.50►
◄multi_speakerfalse►
◄inline_editsfalse►
◄review_each_linefalse►
◄speed_timing_multiplier1.00►
CategoryWorkflowX/Audio/AuK
Inputs (17)
| Name | Type | Default | Description |
|---|---|---|---|
| model | WORKFLOWX_AUK_MODEL | — | |
| encoder | WORKFLOWX_AUK_ENCODER | — | |
| vae | VAE | — | |
| reference_audio | AUDIO | The first speaker's recording. Used for every line when Multi-speaker is off. | |
| script | STRING | [Happy] Hello there, how are you? (3s) [Shy][c-whisper] This is our little secret. | Write one spoken line per row. Start with one optional voice style and any conversions. End with (3s) to choose the original length. |
| words_per_second | FLOAT | 2.00.01–100 | Estimates the length of lines without a duration. Higher values allow less time for the same words. |
| gap_seconds | FLOAT | 0.000–3600 | Adds silence between finished lines. |
| seed | INT | 00–18446744073709550000 | Keep this number and choose fixed to repeat the same random choices. Change it to try a different performance. |
| steps | INT | 321–1000 | Controls how much refinement is used. Start with 32. More can take longer; Flash chooses its own setting. |
| guidance | FLOAT | 2.00–100 | Controls how strongly the voice follows your request. Start with 2. Flash chooses its own setting. |
| sway | FLOAT | -1.00-1–0 | Fine-tunes how the sound is refined. Leave at -1 unless you want to experiment. Flash chooses its own setting. |
| sound_extra_secondsopt | FLOAT | 0.500–3600 | Allows additional time for each laugh, cough, or other sound you add. |
| reference_audio_2opt | AUDIO | The second speaker's recording. Needed when a line uses @voice2 with Multi-speaker on. | |
| multi_speakeropt | BOOLEAN | false | Use @voice1 or @voice2 before a line's tags. Unmarked lines continue the previous speaker, starting with Voice 1. Turn off to use Voice 1 for all lines. |
| inline_editsopt | BOOLEAN | false | Select words to change their delivery or add a sound before them. Turn off to speak the words without these changes. |
| review_each_lineopt | BOOLEAN | false | Generate all lines and send the recording onward. Browse, regenerate, or add lines here, then Finalize to send your revised recording. |
| speed_timing_multiplieropt | FLOAT | 1.000.01–100 | Extra room for speech controlled by speed tags. 1 uses the calculated duration; higher values allow more time. Lines without speed changes are unaffected. |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| audio | AUDIO | — |
| segment_report | STRING | — |