FlowiseAI/Flowise · error · Error

This model does not support audio

Error message

This model does not support audio

What it means

Thrown inside fromStandardAudioBlock (line 166) when an audio block is converted for a non-multimodal Gemini model. Same isMultimodalModel gate as the image/file blocks; only multimodal Gemini variants accept audio input.

Source

Thrown at packages/components/nodes/chatmodels/ChatGoogleGenerativeAI/FlowiseChatGoogleGenerativeAI.ts:166

                            fileUri: block.url
                        }
                    }
                }
            }
            if (block.source_type === 'base64') {
                return {
                    inlineData: {
                        mimeType: block.mime_type ?? '',
                        data: block.data
                    }
                }
            }
            throw new Error(`Unsupported source type: ${block.source_type}`)
        },

        fromStandardAudioBlock(block): FileDataPart | InlineDataPart {
            if (!isMultimodalModel) {
                throw new Error('This model does not support audio')
            }
            if (block.source_type === 'url') {
                const data = parseBase64DataUrl({ dataUrl: block.url })
                if (data) {
                    return {
                        inlineData: {
                            mimeType: data.mime_type,
                            data: data.data
                        }
                    }
                } else {
                    return {
                        fileData: {
                            mimeType: block.mime_type ?? '',
                            fileUri: block.url
                        }
                    }
                }

View on GitHub (pinned to abe4a8601a)

Solutions

1. Use a multimodal, audio-capable Gemini model (e.g., gemini-1.5-pro, gemini-2.0-flash).
2. Strip audio blocks from the message history before this node, or transcribe audio to text upstream.
3. Verify the model name resolves to an audio-capable variant.

Example fix

// before: model='gemini-1.0' + audio block -> throws
// after:  model='gemini-2.0-flash' + audio block -> supported

const MULTIMODAL_PREFIXES = ['gemini-1.5', 'gemini-2', 'gemini-3']
function isMultimodalGemini(model: string): boolean {
  return MULTIMODAL_PREFIXES.some((p) => model.startsWith(p))
}
function hasAudioBlock(messages: BaseMessage[]): boolean {
  return messages.some((m) => Array.isArray(m.content) && m.content.some((c) => (c as any).type === 'audio'))
}
if (hasAudioBlock(messages) && !isMultimodalGemini(model)) {
  throw new Error(`Model ${model} cannot accept audio`)`
}

function hasAudio(c: unknown): boolean {
  return typeof c === 'object' && c !== null && (c as any).type === 'audio'
}

try {
  await chatModel.invoke(messages)
} catch (e) {
  if (e instanceof Error && e.message === 'This model does not support audio') {
    // switch model or transcribe audio to text upstream
  }
  throw e
}

When it happens

Trigger: A standard audio content block is fed to a Gemini model whose _isMultimodalModel flag is false.

Common situations: Text-only Gemini model selected while the chatflow includes audio content, or audio routed to a model variant that lacks audio modality support.

Related errors

• This model does not support images
• This model does not support files
• Invalid media content
• Unsupported source type: ${block.source_type}
• Please provide image as base64 encoded data URL

AI-assisted analysis of FlowiseAI/Flowise@abe4a8601a (2026-08-12). Data as JSON: /api/errors/cb914af2322a03c6. Report an issue: GitHub.