Comfy-Org/ComfyUI · error · ValueError

The prompt references @Audio{max_tag}, but reference mode is

Error message

The prompt references @Audio{max_tag}, but reference mode is '{MODE_TEXT}'. Switch to '{MODE_AUDIO}' and connect the reference clip(s).

What it means

The Seed-OSS audio node uses @Audio{N} tags in the prompt to reference connected clips. If max_audio_tag(text_prompt) finds such a tag but the mode widget is 'text only' (MODE_TEXT), the tag has no meaning and the node refuses to run, telling the user to switch to 'audio reference' mode and connect the clips.

Source

Thrown at comfy_api_nodes/nodes_bytedance.py:3159

        i
        for i in range(1, 3 + 1)
        if reference_mode.get(f"reference_audio_{i}") is not None
    ]


def validate_seed_audio_inputs(
    text_prompt: str,
    mode: str,
    audio_indices: list[int],
    has_image: bool,
    preset_voice: str | None = None,
) -> None:
    validate_string(text_prompt, field_name="text_prompt", min_length=1, max_length=3000)
    max_tag = max_audio_tag(text_prompt)

    if mode == MODE_TEXT:
        if max_tag:
            raise ValueError(
                f"The prompt references @Audio{max_tag}, but reference mode is '{MODE_TEXT}'. "
                f"Switch to '{MODE_AUDIO}' and connect the reference clip(s)."
            )
    elif mode == MODE_AUDIO:
        if not audio_indices:
            raise ValueError(
                f"Reference mode '{MODE_AUDIO}' requires at least one reference_audio input "
                f"(or switch to '{MODE_TEXT}')."
            )
        if audio_indices != list(range(1, len(audio_indices) + 1)):
            raise ValueError(
                "Connect reference_audio inputs in order without gaps: reference_audio_1, then _2, then _3."
            )
        if max_tag > len(audio_indices):
            raise ValueError(
                f"The prompt references @Audio{max_tag}, but only {len(audio_indices)} "
                f"reference audio(s) are connected."
            )

View on GitHub (pinned to 1c6d8d45b3)

Solutions

1. Switch the mode widget to 'audio reference' and connect the referenced clips.
2. Or remove all @Audio tags from the prompt to run pure text-to-sound.

from comfy_api_nodes.nodes_bytedance import max_audio_tag, MODE_TEXT
if mode == MODE_TEXT and max_audio_tag(text_prompt):
    raise ValueError("remove @Audio tags or switch mode to audio reference")

def prompt_has_audio_tags(prompt: str) -> bool:
    return max_audio_tag(prompt) > 0

When it happens

Trigger: Calling the audio generation node with mode='text only' while text_prompt contains '@Audio1' or higher (max_audio_tag returns > 0).

Common situations: Starting from an audio-reference template but leaving the mode widget on text only; hand-editing prompts that retain @Audio tags from an earlier workflow.

Related errors

• Reference mode '{MODE_AUDIO}' requires at least one referenc
• Connect reference_audio inputs in order without gaps: refere
• 'thinking' can only be disabled for text-to-image; enable it
• Only a single input image is supported.
• Seedance read this prompt as editing the reference video, an

AI-assisted analysis of Comfy-Org/ComfyUI@1c6d8d45b3 (2026-08-14). Data as JSON: /api/errors/89440d44ea59afdb. Report an issue: GitHub.