Comfy-Org/ComfyUI · error · ValueError

@AudioN tags are not used in '{MODE_IMAGE}' mode; the prompt

Error message

@AudioN tags are not used in '{MODE_IMAGE}' mode; the prompt should contain only the text to synthesize.

What it means

Thrown by the ByteDance Seed Audio node when reference_mode is 'image reference' and the prompt still contains @AudioN tags. In image mode the model takes voice characteristics from the reference image; @AudioN tags are not interpreted and the prompt should be plain synthesis text. max_tag being non-zero means the tag parser found at least one @AudioN reference.

Source

Thrown at comfy_api_nodes/nodes_bytedance.py:3182

        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."
            )
    elif mode == MODE_IMAGE:
        if not has_image:
            raise ValueError(f"Reference mode '{MODE_IMAGE}' requires a reference_image input.")
        if max_tag:
            raise ValueError(
                f"@AudioN tags are not used in '{MODE_IMAGE}' mode; the prompt should contain "
                f"only the text to synthesize."
            )
    elif mode == MODE_SPEAKER:
        if not preset_voice or preset_voice not in SEED_AUDIO_VOICE_MAP:
            raise ValueError(f"Reference mode '{MODE_SPEAKER}' requires selecting a preset voice.")
        if max_tag > 1:
            raise ValueError(
                f"'{MODE_SPEAKER}' mode uses a single voice, so @Audio{max_tag} is out of range. "
                f"Remove the @AudioN tags — the whole prompt is read in the selected voice."
            )
    else:
        raise ValueError(f"Unknown reference mode: {mode!r}")


class ByteDanceSeedAudioNode(IO.ComfyNode):

    @classmethod

View on GitHub (pinned to 1c6d8d45b3)

Solutions

Strip all @AudioN tags from the prompt so it contains only the text to synthesize.
If you intended per-clip voice cloning, switch reference_mode back to 'audio reference' and connect the matching reference_audio inputs.

Example fix

// before: prompt = "<@Audio1>Hello there" (mode: image reference)
// after:  prompt = "Hello there" (mode: image reference)

Defensive patterns

Strategy: validation

Validate before calling

import re

def strip_audio_tags_for_mode(prompt: str, mode: str) -> str:
    if mode == "image reference":
        return re.sub(r"@Audio\d+", "", prompt).strip()
    return prompt

Prevention

When changing reference_mode, re-read the prompt and remove tags the new mode does not use.
Maintain separate prompt templates per mode (tagged for audio reference, plain for image/preset).

When it happens

Trigger: reference_mode == 'image reference', a reference image IS connected, but the text_prompt contains one or more @AudioN tags (max_tag > 0).

Common situations: User reuses a multi-speaker dialogue prompt written for 'audio reference' mode after switching the mode dropdown to 'image reference'; template prompts that always include speaker tags.

Related errors

AI-assisted analysis of Comfy-Org/ComfyUI@1c6d8d45b3 (2026-08-14). Data as JSON: /api/errors/1e5bbf02958fd0fb. Report an issue: GitHub.