BerriAI/litellm · error · ValueError

SSML input is required when use_ssml is True.

Error message

SSML input is required when use_ssml is True.

What it means

Raised by validate_vertex_input when the Vertex text-to-speech request has use_ssml=True but the input contains neither 'text' nor 'ssml'. The validator first strips None values and, when use_ssml is set, converts any 'text' entry into 'ssml'; this error fires only when both keys are absent after that cleanup, meaning the caller enabled SSML mode without supplying any content at all.

Source

Thrown at litellm/llms/vertex_ai/text_to_speech/text_to_speech_handler.py:222

        http_binary_response: Final = HttpxBinaryResponseContent(response)
        return http_binary_response


def validate_vertex_input(input_data: VertexInput, kwargs: dict, optional_params: dict) -> None:
    # Remove None values
    if input_data.get("text") is None:
        input_data.pop("text", None)
    if input_data.get("ssml") is None:
        input_data.pop("ssml", None)

    # Check if use_ssml is set
    use_ssml: Final = kwargs.get("use_ssml", optional_params.get("use_ssml", False))

    if use_ssml:
        if "text" in input_data:
            input_data["ssml"] = input_data.pop("text")
        elif "ssml" not in input_data:
            raise ValueError("SSML input is required when use_ssml is True.")
    else:
        # LiteLLM will auto-detect if text is in ssml format
        # check if "text" is an ssml - in this case we should pass it as ssml instead of text
        if input_data:
            _text: Final = input_data.get("text", None) or ""
            if "<speak>" in _text:
                input_data["ssml"] = input_data.pop("text")

    if not input_data:
        raise ValueError("Either 'text' or 'ssml' must be provided.")
    if "text" in input_data and "ssml" in input_data:
        raise ValueError("Only one of 'text' or 'ssml' should be provided, not both.")

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. When use_ssml=True, pass the SSML markup via the ssml/input parameter instead of plain text.
2. Set use_ssml=False (or omit it) if you intend to synthesize plain text.

When it happens

Trigger: Thrown at litellm/llms/vertex_ai/text_to_speech/text_to_speech_handler.py:222 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of BerriAI/litellm@77b7c6c40c (2026-08-18). Data as JSON: /api/errors/911f7cb1b6dcf94d. Report an issue: GitHub.