Breeze TTS 2 Voice Direction

Speaks a line in a voice cloned from a short reference clip, directed in plain English: tone, emotion, pace and delivery. Breeze TTS 2 (3.5B, bf16 weights) via the ComfyUI-Breeze-TTS-2 custom nodes (https://github.com/saganaki22/ComfyUI-Breeze-TTS-2); weights download on first run. Writes a 24 kHz mono FLAC. Model weights and self-hosted outputs are for research and non-commercial use only: https://huggingface.co/BreezeBlue/Breeze-TTS-2/blob/main/LICENSE

Workflow id: breeze_tts2_direction · Text → Speech

Calling it

POST /api/image/generate
{
  "workflow": "breeze_tts2_direction",
  "prompt": "...",
  "audio": "...",
  "reference_text": "...",
  "instruction": "..."
}

Params

Every input this workflow takes. Your install is the source of truth:GET /api/workflows/breeze_tts2_direction returns these as they are on your machine.

• prompt · str · required
  The line to speak. Sounds go inline in parentheses, e.g. (laugh), (sigh), (cough), (clears throat). How it should sound goes in `instruction`, not here.
• audio · str · required
  Reference clip of the voice to clone, staged to the run node.
• reference_text · str · required
  The exact transcript of the reference clip, word for word.
• instruction · str · required
  How to deliver the line, in plain English: tone, emotion, pace and delivery, e.g. "Speak slowly with a restrained, serious tone."
• cfg · float · default 4
  How strongly the instruction steers delivery. 4 is the author's setting for Voice Direction.
• seed · int · optional
  Optional. Leave it out and every run is a new random take. Send a seed only to remake a take exactly: the seed a job used is in its record.