BerriAI/litellm · error · ValueError

RUNWAYML_API_SECRET or RUNWAYML_API_KEY is not set

Error message

RUNWAYML_API_SECRET or RUNWAYML_API_KEY is not set

What it means

Credential guard in the RunwayML TTS config's validate_environment: the key chain (argument, RUNWAYML_API_SECRET, RUNWAYML_API_KEY) resolved nothing, so auth headers cannot be built and the TTS request is rejected before sending.

Source

Thrown at litellm/llms/runwayml/text_to_speech/transformation.py:207

        # Return None for voice string since RunwayML uses dict format
        return None, mapped_params

    def validate_environment(
        self,
        headers: dict,
        model: str,
        api_key: str | None = None,
        api_base: str | None = None,
    ) -> dict:
        """
        Validate RunwayML environment and set up authentication headers
        """
        validated_headers: Final = headers.copy()

        final_api_key: Final = api_key or get_secret_str("RUNWAYML_API_SECRET") or get_secret_str("RUNWAYML_API_KEY")

        if not final_api_key:
            raise ValueError("RUNWAYML_API_SECRET or RUNWAYML_API_KEY is not set")

        validated_headers["Authorization"] = f"Bearer {final_api_key}"
        validated_headers["X-Runway-Version"] = RUNWAYML_DEFAULT_API_VERSION
        validated_headers["Content-Type"] = "application/json"

        return validated_headers

    def get_complete_url(
        self,
        model: str,
        api_base: str | None,
        litellm_params: dict,
    ) -> str:
        """
        Get the complete URL for RunwayML TTS request
        """
        complete_url = api_base or get_secret_str("RUNWAYML_API_BASE") or self.DEFAULT_BASE_URL

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Set RUNWAYML_API_SECRET (or RUNWAYML_API_KEY) environment variable.
2. Or pass api_key to the speech call.

Example fix

litellm.speech(model="runwayml/...", api_key="<key>", input=...)

When it happens

Trigger: Triggered when calling RunwayML text-to-speech without RUNWAYML_API_SECRET or RUNWAYML_API_KEY set.

Common situations: See trigger scenarios.

AI-assisted analysis of BerriAI/litellm@77b7c6c40c (2026-08-18). Data as JSON: /api/errors/24695a84b0bfe1bf. Report an issue: GitHub.