Nodes/FireRedTTS3-ComfyUI/FireRedTTS3 Semantic Edit
ComfyUI Node

FireRedTTS3 Semantic Edit

Semantic speech editing (insert/delete/replace words) with FireRedTTS3-Instruct.

By Saganaki22·Created 11 days ago·Updated 7 days ago· 17
FireRedTTS3 Semantic Edit
  • firered_model
  • audio
  • audio
  • edited_text
instructionReplace 'cats' with 'dogs'.
n_timesteps10
inference_cfg1.20
stop_threshold0.50
seed42
max_audio_seconds64
CategoryFireRedTTS3

Inputs (8)

NameTypeDefaultDescription
firered_modelFIREREDTTS3_MODEL
audioAUDIOInput speech to edit.
instructionSTRINGReplace 'cats' with 'dogs'.Content edit instruction: insertion, deletion or substitution, e.g. "insert 'really' after the word at index 8."
n_timestepsINT101–50Flow-matching steps per generated audio patch. 10 is the official default; more is slower with diminishing returns.
inference_cfgFLOAT1.200–4Classifier-free guidance strength for the flow head. 0 disables CFG. Official defaults: 2.0 for cloning, 1.2 for design/edits.
stop_thresholdFLOAT0.500.05–0.95Stop-token probability threshold that ends generation. Higher values allow longer audio.
seedINT420–21474836470 uses the current random state. A positive value is repeatable.
max_audio_secondsFLOAT644–160Hard cap on generated audio length per sentence (64s is the official maximum).

Outputs (2)

NameTypeDescription
audioAUDIO
edited_textSTRING