BerriAI/litellm · error · ValueError

litellm_params is required

Error message

litellm_params is required

What it means

validate_input_kwargs in the speech-to-completion bridge raises ValueError("litellm_params is required") when kwargs["litellm_params"] is missing, None, or not a dict. litellm_params carries router/proxy-level settings (api_base, api_key, metadata, ...) and is spread verbatim into the bridged litellm.completion call (transformation.py:44), so the bridge refuses to run without it.

Solutions

1. Pass a dict ({} is acceptable): handler.speech(..., litellm_params={}, ...).
2. Include credentials there when needed: litellm_params={"api_key": ..., "api_base": ...}.
3. Use litellm.speech() so litellm builds litellm_params itself.

Example fix

# before
handler.speech(model="gpt-4o-audio-preview", input="hi", voice="alloy", optional_params={}, headers={}, logging_obj=log, custom_llm_provider="openai")  # ValueError: litellm_params is required

# after
handler.speech(model="gpt-4o-audio-preview", input="hi", voice="alloy", optional_params={}, litellm_params={"api_key": os.environ["OPENAI_API_KEY"]}, headers={}, logging_obj=log, custom_llm_provider="openai")

def check_litellm_params(kwargs: dict) -> None:
    if not isinstance(kwargs.get("litellm_params"), dict):
        raise ValueError("speech bridge requires dict 'litellm_params' (use {} if none)")

def is_valid_litellm_params(value: object) -> bool:
    return isinstance(value, dict)

When it happens

Trigger: Direct handler invocations that omit litellm_params or pass None; constructing kwargs manually from a request that never carried litellm params (bare SDK usage outside the proxy).

Common situations: Code lifted from proxy internals into a standalone script; tests with minimal kwargs dicts; None defaults from de-serialized request objects.

Understand the failure class

Background: "missing required argument" and "the following required arguments were not provided": what required-argument errors mean and how to fix them — this error's family across 20 libraries.

Related errors

• custom_llm_provider is required
• headers is required
• input is required
• logging_obj is required
• model is required

AI-assisted analysis of BerriAI/litellm@77b7c6c40c (2026-08-18). Data as JSON: /api/errors/eb44cd92c9142130. Report an issue: GitHub.

Appendix: source

Thrown at litellm/endpoints/speech/speech_to_completion_bridge/handler.py:53

        model: Final = kwargs.get("model")
        if model is None or not isinstance(model, str):
            raise ValueError("model is required")

        custom_llm_provider: Final = kwargs.get("custom_llm_provider")
        if custom_llm_provider is None or not isinstance(custom_llm_provider, str):
            raise ValueError("custom_llm_provider is required")

        input: Final = kwargs.get("input")
        if input is None or not isinstance(input, str):
            raise ValueError("input is required")

        optional_params: Final = kwargs.get("optional_params")
        if optional_params is None or not isinstance(optional_params, dict):
            raise ValueError("optional_params is required")

        litellm_params: Final = kwargs.get("litellm_params")
        if litellm_params is None or not isinstance(litellm_params, dict):
            raise ValueError("litellm_params is required")

        headers = kwargs.get("headers")
        if headers is None or not isinstance(headers, dict):
            raise ValueError("headers is required")

        headers = kwargs.get("headers")
        if headers is None or not isinstance(headers, dict):
            raise ValueError("headers is required")

        logging_obj: Final = kwargs.get("logging_obj")
        if logging_obj is None or not isinstance(logging_obj, LiteLLMLoggingObj):
            raise ValueError("logging_obj is required")

        return SpeechToCompletionBridgeHandlerInputKwargs(
            model=model,
            input=input,
            voice=kwargs.get("voice"),
            optional_params=optional_params,

View on GitHub (pinned to 77b7c6c40c)