Comfy-Org/ComfyUI · error · ValueError

The prompt references @Audio{idx}, but only voices 1..{len(v

Error message

The prompt references @Audio{idx}, but only voices 1..{len(voices)} exist.

What it means

Grok @AudioN tag resolution failure where the index is entirely out of range: idx exceeds the number of voice slots (len(voices)), so no voice_{idx} exists at all. Distinct from the 'none' case — here the slot itself is missing. Raised inside the regex substitution loop, before any API call is made.

Source

Thrown at comfy_api_nodes/nodes_grok.py:119

    audio_indices: dict[int, int] = {}
    for slot, voice in enumerate(voices, start=1):
        if voice != "none":
            audio_indices[slot] = len(audio_indices)

    def repl(match: re.Match) -> str:
        kind = match.group(1).lower()
        idx = int(match.group("idx") or 1)
        if kind == "image":
            if not 1 <= idx <= total_images:
                raise ValueError(
                    f"The prompt references @Image{idx}, but only {total_images} "
                    f"reference images are connected (a batched input counts once per image)."
                )
            return f"<IMAGE_{idx - 1}>"
        if idx not in audio_indices:
            if 1 <= idx <= len(voices):
                raise ValueError(f"The prompt references @Audio{idx}, but 'voice_{idx}' is set to 'none'.")
            raise ValueError(f"The prompt references @Audio{idx}, but only voices 1..{len(voices)} exist.")
        return f"<AUDIO_{audio_indices[idx]}>"

    prev = None
    while prev != prompt:
        prev = prompt
        prompt = _GROK_REF_TAG_RE.sub(repl, prompt)
    return prompt


def _extract_grok_price(response) -> float | None:
    if response.usage and response.usage.cost_in_usd_ticks is not None:
        return response.usage.cost_in_usd_ticks / 10_000_000_000
    return None


def _extract_grok_video_price(response) -> float | None:
    price = _extract_grok_price(response)
    if price is not None:

View on GitHub (pinned to 1c6d8d45b3)

Solutions

1. Change the tag to a valid slot: @Audio1..@Audio{len(voices)}.
2. Add the missing voice input(s) to the node so the index exists.
3. Remove the tag if that voice is no longer used.

Example fix

# before: 3 voice slots
prompt = "@Audio4 sings the chorus"  # raises

# after
prompt = "@Audio3 sings the chorus"

refs = {int(m.group("idx") or 1) for m in _TAG.finditer(prompt) if m.group(1).lower() == "audio"}
out_of_range = [i for i in refs if i > len(voices)]
assert not out_of_range, f"tags exceed {len(voices)} voice slots: {out_of_range}"

When it happens

Trigger: Prompt contains e.g. '@Audio4' while only 3 voice inputs exist (voices list length 3), or '@Audio' with zero voices configured (idx defaults to 1, and 1 <= idx <= 0 is impossible).

Common situations: Prompt templates written for more voice slots than the node version exposes; deleting voice inputs after writing the prompt; typo like '@Audio7' instead of '@Audio1'; assuming default-voice tagging works with no voices connected.

Related errors

• The prompt references @Audio{idx}, but 'voice_{idx}' is set
• The prompt references @Image{idx}, but only {total_images} r
• The pro model supports only 1 input image.
• A maximum of 3 input images is supported.
• Custom aspect ratio is only allowed when multiple images are

AI-assisted analysis of Comfy-Org/ComfyUI@1c6d8d45b3 (2026-08-14). Data as JSON: /api/errors/044a5182aea95e01. Report an issue: GitHub.