Comfy-Org/ComfyUI · error · ValueError

The prompt references @Audio{max_tag}, but only {len(audio_i

Error message

The prompt references @Audio{max_tag}, but only {len(audio_indices)} reference audio(s) are connected.

What it means

Thrown by the ByteDance Seed Audio 1.0 node when the text prompt contains an @AudioN tag whose index N exceeds the number of connected reference_audio inputs. The node parses @AudioN tags out of the prompt in 'audio reference' mode and requires one connected audio input per tag. It is a workflow-wiring validation error raised before any API call is made.

Source

Thrown at comfy_api_nodes/nodes_bytedance.py:3174

    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."
            )
    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."

View on GitHub (pinned to 1c6d8d45b3)

Solutions

  1. Connect additional reference_audio_N inputs up to the highest @AudioN index used in the prompt (ensure they are wired in order: _1, then _2, then _3).
  2. Or edit the prompt so the highest @AudioN tag does not exceed the number of connected reference audios (e.g. change '@Audio3' to '@Audio2' or remove it).
  3. If you only have one voice clip, switch reference_mode to 'preset voice' and drop the @AudioN tags entirely.

Example fix

// before: prompt = "<@Audio1>Hi<@Audio3>Bye" with only reference_audio_1 connected
// after:  prompt = "<@Audio1>Hi<@Audio2>Bye" with reference_audio_1 and reference_audio_2 connected
Defensive patterns

Strategy: validation

Validate before calling

import re

def check_audio_tags(prompt: str, num_reference_audios: int) -> None:
    tags = [int(n) for n in re.findall(r"@Audio(\d+)", prompt)]
    if tags and max(tags) > num_reference_audios:
        raise ValueError(f"prompt uses @Audio{max(tags)} but only {num_reference_audios} reference audios connected")

Prevention

When it happens

Trigger: Node reference_mode is 'audio reference', audio_indices is non-empty and gap-free, but max_tag (the highest @AudioN index found in the prompt) is greater than len(audio_indices). E.g. prompt contains '@Audio3' while only reference_audio_1 and reference_audio_2 are connected.

Common situations: User edits the prompt to add a third speaker tag but forgets to wire reference_audio_3; copying a workflow that had more reference audios than the current copy; batching a multi-speaker dialogue script with more @AudioN tags than available voice clips.

Related errors

AI-assisted analysis of Comfy-Org/ComfyUI@1c6d8d45b3 (2026-08-14). Data as JSON: /api/errors/9e2a84e1977c72ae. Report an issue: GitHub.