calesthio/OpenMontage · error · ValueError

each reference audio duration must be 2 to {max_reference_se

Error message

each reference audio duration must be 2 to {max_reference_seconds} seconds

What it means

Raised when any entry in reference_audio_durations is under 2 seconds or over the reference cap (15s standard variants, 30s on 2.5). Each audio clip hint must fall inside the window Ark can actually use.

Source

Thrown at tools/video/seedance_ark.py:830

            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"
                    )
            local_audio_durations = [
                duration
                for ref in audio_refs
                if (
                    duration := self._local_or_data_audio_duration(
                        str(ref), max_seconds=max_reference_seconds
                    )
                )

View on GitHub (pinned to 95e1c3d0ab)

Solutions

1. Clamp each duration entry to the 2..15 (or 2..30 on 2.5) range
2. Trim or loop source audio so the referenced window is inside the range
3. Use model_variant='2.5' for clips up to 30s

Example fix

# before
inputs = {"reference_audio_durations": [1, 3000]}

# after
inputs = {"reference_audio_durations": [2, 15]}

max_s = 30 if str(inputs.get("model_variant", "standard")).lower() == "2.5" else 15
assert all(2 <= float(d) <= max_s for d in inputs.get("reference_audio_durations") or [])

def valid_audio_durations(durations: list, max_s: int = 15) -> bool:
    return all(2 <= float(d) <= max_s for d in durations or [])

When it happens

Trigger: A durations entry of 1, 0.5, 20 (non-2.5), or 45 (2.5); passing milliseconds like 3000 instead of seconds.

Common situations: Referencing very short stingers or long music beds; assuming audio has no duration limits; unit confusion between ms and s.

Related errors

• all reference audio clips together must be at most {max_refe
• all local reference audio clips together must be at most {ma
• each reference video duration must be 2 to {max_reference_se
• all reference videos together must be at most {max_reference
• reference_to_video accepts at most 3 reference audio clips (

AI-assisted analysis of calesthio/OpenMontage@95e1c3d0ab (2026-08-15). Data as JSON: /api/errors/936eb43b221f9482. Report an issue: GitHub.