calesthio/OpenMontage · error · ValueError

model_id must be one of: {choices}

Error message

model_id must be one of: {choices}

What it means

Raised by fal_elevenlabs_tts._resolve_model when the requested model_id (after alias mapping) is not a key in _MODELS. The wrapper whitelists supported ElevenLabs models on fal.ai and maps aliases first, so this only fires for genuinely unknown names.

Source

Thrown at tools/audio/fal_elevenlabs_tts.py:215

        "writes an audio file to output_path",
        "submits one paid fal.ai ElevenLabs speech request",
    ]
    user_visible_verification = [
        "Listen to the generated voice sample before approving full narration",
    ]

    def _get_api_key(self) -> str | None:
        return os.environ.get("FAL_KEY") or os.environ.get("FAL_AI_API_KEY")

    def get_status(self) -> ToolStatus:
        return ToolStatus.AVAILABLE if self._get_api_key() else ToolStatus.UNAVAILABLE

    def _resolve_model(self, requested: str | None) -> tuple[str, str]:
        model_name = requested or "eleven-v3"
        model_name = self._MODEL_ALIASES.get(model_name, model_name)
        if model_name not in self._MODELS:
            choices = ", ".join(self._MODELS)
            raise ValueError(f"model_id must be one of: {choices}")
        return model_name, self._MODELS[model_name]

    def estimate_cost(self, inputs: dict[str, Any]) -> float:
        model_name, _ = self._resolve_model(inputs.get("model_id"))
        return round(
            len(inputs.get("text", "")) * self._PRICE_PER_CHARACTER[model_name],
            4,
        )

    @staticmethod
    def _output_extension(output_format: str) -> str:
        return {
            "mp3": "mp3",
            "pcm": "pcm",
            "opus": "opus",
        }.get(output_format.split("_", 1)[0], "audio")

    def execute(self, inputs: dict[str, Any]) -> ToolResult:

View on GitHub (pinned to 95e1c3d0ab)

Solutions

1. Use one of the listed choices — typically 'eleven-v3' (the default) or 'eleven-multilingual-v2'
2. If an alias should exist, add the mapping to _MODEL_ALIASES in fal_elevenlabs_tts.py
3. Omit model_id entirely to get the default eleven-v3

Example fix

// before
inputs = {"text": "hi", "model_id": "tts-1"}  # raises

// after
inputs = {"text": "hi", "model_id": "eleven-v3"}

valid = set(tool._MODELS) | set(tool._MODEL_ALIASES)
if inputs.get("model_id") and inputs["model_id"] not in valid:
    inputs["model_id"] = "eleven-v3"  # or surface a choice list

def is_valid_fal_tts_model(model_id: str | None, tool) -> bool:
    name = tool._MODEL_ALIASES.get(model_id, model_id)
    return name in tool._MODELS

When it happens

Trigger: Passing model_id like 'eleven-turbo-v2-5' or 'tts-1' that is neither in _MODEL_ALIASES nor _MODELS; also raised from estimate_cost, so cost-checking a bad model fails the same way.

Common situations: Copy-pasting model names from OpenAI or ElevenLabs native docs that fal.ai does not host; new model released upstream before this wrapper's whitelist is updated; typo in a config file.

Related errors

• duration_seconds is required for cost estimation
• text is required
• text exceeds Kling TTS safety limit of 5000 characters
• voice_id is required for Kling official TTS
• voice_language must be one of: {', '.join(TTS_LANGUAGES)}

AI-assisted analysis of calesthio/OpenMontage@95e1c3d0ab (2026-08-15). Data as JSON: /api/errors/c8748adfe6e8dec1. Report an issue: GitHub.