Nodes/FireRedTTS3-ComfyUI/FireRedTTS3 Load Model
ComfyUI Node

FireRedTTS3 Load Model

Load FireRedTTS3 (base or instruct) natively with ComfyUI/AIMDO memory registration.

By Saganaki22·Created 11 days ago·Updated 7 days ago· 17
FireRedTTS3 Load Model
    • firered_model
    repoFireRedTTS3-bf16
    variantfireredtts3_instruct
    dtypeauto
    deviceauto
    attentionauto
    download_if_missingtrue
    CategoryFireRedTTS3

    Inputs (6)

    NameTypeDefaultDescription
    repoCOMBOFireRedTTS3-bf16Weight source. bf16 keeps the flow head/decoder in fp32 and matches official mixed-precision compute (recommended). int8 ConvRot quantizes the transformer linears (smallest, experimental). fp32 is the official full-precision repo. Missing files download when download_if_missing is on; otherwise the error tells you where to place them.
    variantCOMBOfireredtts3_instructbase: zero-shot cloning in 24 languages + 21 Chinese dialects using language tags. instruct: voice design (Chinese/English only) + speech editing; its cloning inherits the language from the reference audio (no language tags).
    dtypeCOMBOautobf16 stores the backbone LLM and RedAE encoder in bf16 (same compute as the official autocast path) and keeps the flow head/decoder fp32. fp32 is full precision. auto picks bf16 on supported GPUs.
    deviceCOMBOautoDevice for inference. auto follows ComfyUI's current torch device; cpu is a slow fallback.
    attentionCOMBOautoAttention backend for the Qwen3 transformers. auto uses flash_attention when flash_attn is installed and compatible (CUDA + bf16 compute), else sdpa. The fp32 RedAE decoder always uses sdpa.
    download_if_missingBOOLEANtrueDownload the selected weights, RedAE codec, tokenizer, CAM++ and FastText language-ID files into ComfyUI/models/fireredtts3 when missing.

    Outputs (1)

    NameTypeDescription
    firered_modelFIREREDTTS3_MODEL