calesthio/OpenMontage · error · ValueError

Kling identify_face requires video_id or video_url

Error message

Kling identify_face requires video_id or video_url

What it means

ValueError from _build_identify_request when the payload ends up empty: neither video_id nor video_url was provided (and no video_path trigger from the sibling guard). Face identification operates on an existing video, so exactly one of these references is required.

Source

Thrown at tools/avatar/kling_lip_sync.py:357

                **self._callback_result_data(inputs, task_id),
                **probed,
            },
            artifacts=[str(path) for path in paths],
            cost_usd=self.estimate_cost(inputs),
            duration_seconds=round(time.time() - start, 2),
            model="kling-official-lip-sync",
        )

    def _build_identify_request(self, inputs: dict[str, Any]) -> dict[str, Any]:
        if inputs.get("video_path") and not (inputs.get("video_url") or inputs.get("video_id")):
            raise ValueError("Kling identify_face requires video_url or video_id; local video paths cannot be silently uploaded.")
        payload: dict[str, Any] = {}
        if inputs.get("video_id"):
            payload["video_id"] = str(inputs["video_id"])
        if inputs.get("video_url"):
            payload["video_url"] = str(inputs["video_url"])
        if not payload:
            raise ValueError("Kling identify_face requires video_id or video_url")
        return {
            "path": "/v1/videos/identify-face",
            "payload": payload,
            "operation": "identify_face",
        }

    def _build_advanced_request(self, inputs: dict[str, Any]) -> dict[str, Any]:
        session_id = str(inputs.get("session_id") or "").strip()
        if not session_id:
            raise ValueError("advanced_lip_sync requires session_id")
        face_choose = self._normalize_face_choose(inputs)
        if not face_choose:
            raise ValueError("advanced_lip_sync requires face_choose or face_id")
        if len(face_choose) != 1:
            raise ValueError("advanced_lip_sync currently supports exactly one face_choose item")
        face_item = face_choose[0]
        audio_source = self._copy_audio_input(inputs, face_item)
        self._copy_timing_fields(inputs, face_item)

View on GitHub (pinned to 95e1c3d0ab)

Solutions

1. Pass video_id (from a prior Kling upload) or video_url (public HTTPS URL) in the inputs.
2. If the video is local, see the explicit-upload requirement (upload first — do not use video_path).
3. Log the inputs dict before calling to confirm which keys are actually present.

Example fix

// before
result = tool.run({"operation": "identify_face"})

// after
result = tool.run({"operation": "identify_face", "video_url": "https://cdn.example.com/clip.mp4"})

assert inputs.get("video_id") or inputs.get("video_url"), \
    "identify_face requires video_id or video_url (upload local files first)"

When it happens

Trigger: Calling kling_lip_sync operation='identify_face' with no video reference at all; passing video under an unrecognized key (e.g. 'file' or 'source').

Common situations: Input dict built dynamically and the video field never got set; key-name confusion between tools.

Related errors

• Kling avatar requires image_url or image_path
• Kling avatar requires audio_id, sound_file, sound_file_url,
• Kling identify_face requires video_url or video_id; local vi
• advanced_lip_sync requires session_id
• advanced_lip_sync requires face_choose or face_id

AI-assisted analysis of calesthio/OpenMontage@95e1c3d0ab (2026-08-15). Data as JSON: /api/errors/75ec06327f983cea. Report an issue: GitHub.