calesthio/OpenMontage · error · ValueError

reference_audio_durations must match the number of reference

Error message

reference_audio_durations must match the number of reference audio clips

What it means

Raised when reference_audio_durations is non-empty and its length differs from the number of audio references. Like the video durations array, audio durations must be a parallel per-clip list matching the collected audio refs exactly.

Source

Thrown at tools/video/seedance_ark.py:822

                        "all reference videos together must be at most "
                        f"{max_reference_seconds} seconds"
                    )

            audio_refs = list(inputs.get("reference_audio_urls") or [])
            audio_refs.extend(inputs.get("reference_audio_paths") or [])
            if inputs.get("reference_audio_url"):
                audio_refs.append(inputs["reference_audio_url"])
            if inputs.get("reference_audio_path"):
                audio_refs.append(inputs["reference_audio_path"])
            if len(audio_refs) > max_audios:
                raise ValueError(
                    "reference_to_video accepts at most 3 reference audio "
                    f"clips (maximum {max_audios})"
                )
            audio_durations = list(inputs.get("reference_audio_durations") or [])
            if audio_durations:
                if len(audio_durations) != len(audio_refs):
                    raise ValueError(
                        "reference_audio_durations must match the number of "
                        "reference audio clips"
                    )
                if any(
                    float(value) < 2 or float(value) > max_reference_seconds
                    for value in audio_durations
                ):
                    raise ValueError(
                        f"each reference audio duration must be 2 to {max_reference_seconds} seconds"
                    )
                if (
                    sum(float(value) for value in audio_durations)
                    > max_reference_seconds
                ):
                    raise ValueError(
                        "all reference audio clips together must be at most "
                        f"{max_reference_seconds} seconds"
                    )

View on GitHub (pinned to 95e1c3d0ab)

Solutions

1. Rebuild reference_audio_durations with one entry per audio ref in the same order
2. Drop reference_audio_durations if per-clip hints are unnecessary

Example fix

# before
inputs = {"reference_audio_urls": [a1, a2],
          "reference_audio_durations": [4]}

# after
inputs = {"reference_audio_urls": [a1, a2],
          "reference_audio_durations": [4, 4]}

durs = list(inputs.get("reference_audio_durations") or [])
if durs:
    assert len(durs) == len(collected_audio_refs(inputs)), "parallel arrays out of sync"

def audio_durations_match(durations: list, audio_refs: list) -> bool:
    return not durations or len(durations) == len(audio_refs)

When it happens

Trigger: len(reference_audio_durations) != len(audio_refs), e.g. 3 durations for 4 clips, or forgetting the singular reference_audio_url contributes to the count.

Common situations: Appending an audio ref without appending a duration; sharing one durations array across requests with varying clip counts.

Related errors

• each reference audio duration must be 2 to {max_reference_se
• all reference audio clips together must be at most {max_refe
• all local reference audio clips together must be at most {ma
• reference_video_durations must match the number of reference
• each reference video duration must be 2 to {max_reference_se

AI-assisted analysis of calesthio/OpenMontage@95e1c3d0ab (2026-08-15). Data as JSON: /api/errors/8c49371667e3b74a. Report an issue: GitHub.