ComfyUI Node
FireRedTTS3 Acoustic Edit
Acoustic speech editing (speed / pitch / volume) with FireRedTTS3-Instruct.
FireRedTTS3 Acoustic Edit
- firered_model
- audio
- audio
◄modespeed►
◄value0.5►
◄n_timesteps10►
◄inference_cfg1.20►
◄stop_threshold0.50►
◄seed42►
◄max_audio_seconds64►
◄custom_instruction►
CategoryFireRedTTS3
Inputs (10)
| Name | Type | Default | Description |
|---|---|---|---|
| firered_model | FIREREDTTS3_MODEL | — | |
| audio | AUDIO | Input speech to transform. | |
| mode | COMBO | speed | Acoustic attribute to edit. Uses the model's trained instruction templates. |
| value | FLOAT | 0.5-6–6 | speed: 0.5-2.0 (rate multiplier). volume: 0.3-2.0 (gain multiplier). pitch: -6 to +6 semitone-like steps (rounded to an integer, not 0). |
| n_timesteps | INT | 101–50 | Flow-matching steps per generated audio patch. 10 is the official default; more is slower with diminishing returns. |
| inference_cfg | FLOAT | 1.200–4 | Classifier-free guidance strength for the flow head. 0 disables CFG. Official defaults: 2.0 for cloning, 1.2 for design/edits. |
| stop_threshold | FLOAT | 0.500.05–0.95 | Stop-token probability threshold that ends generation. Higher values allow longer audio. |
| seed | INT | 420–2147483647 | 0 uses the current random state. A positive value is repeatable. |
| max_audio_seconds | FLOAT | 644–160 | Hard cap on generated audio length per sentence (64s is the official maximum). |
| custom_instructionopt | STRING | Optional raw instruction override (e.g. 'adjust the speed to 0.5x'). Leave empty to build it from mode + value. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| audio | AUDIO | — |