BerriAI/litellm · error · ValueError

Unsupported audio format for Gemini TTS models: {audio_forma

Error message

Unsupported audio format for Gemini TTS models: {audio_format}. Gemini TTS models only support 'pcm16' format as they return audio data in L16 PCM format. Please set audio format to 'pcm16'.

What it means

Error "Unsupported audio format for Gemini TTS models: {audio_format}. Gemini TTS models only support 'pcm16' format as they return audio data in L16 PCM format. Please set audio format to 'pcm16'." thrown in BerriAI/litellm.

Source

Thrown at litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py:1026

        speechConfig = {
            voiceConfig: {
                prebuiltVoiceConfig: {
                    voiceName: "alloy",
                }
            },
            languageCode: "en-US",
        }
        """
        from litellm.types.llms.vertex_ai import (
            PrebuiltVoiceConfig,
            SpeechConfig,
            VoiceConfig,
        )

        # Validate audio format - Gemini TTS only supports pcm16
        audio_format: Final = value.get("format")
        if audio_format is not None and audio_format != "pcm16":
            raise ValueError(
                f"Unsupported audio format for Gemini TTS models: {audio_format}. "
                f"Gemini TTS models only support 'pcm16' format as they return audio data in L16 PCM format. "
                f"Please set audio format to 'pcm16'."
            )

        # Map OpenAI audio parameter to Gemini speech config
        speech_config: Final[SpeechConfig] = {}

        if "voice" in value:
            prebuilt_voice_config: Final[PrebuiltVoiceConfig] = {"voiceName": value["voice"]}
            voice_config: Final[VoiceConfig] = {"prebuiltVoiceConfig": prebuilt_voice_config}
            speech_config["voiceConfig"] = voice_config

        if "language_code" in value:
            speech_config["languageCode"] = value["language_code"]

        return cast(dict, speech_config)

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Set audio format to 'pcm16' for Gemini TTS models.

Example fix

litellm.speech(..., response_format="pcm16")  # audio format pcm16

When it happens

Trigger: Triggered when an audio format other than 'pcm16' is requested for Gemini TTS models.

Common situations: See trigger scenarios.

AI-assisted analysis of BerriAI/litellm@77b7c6c40c (2026-08-18). Data as JSON: /api/errors/1185a314b442e74c. Report an issue: GitHub.