ToolsPromptsSkillsWorkflowsBlogAbout

Multi-Modal Prompting — combine text, images, and audio in one prompt

Structure prompts that include images, audio, and text together, with clear instructions on how each modality should be used.

Prompting4.4
Multi-Modal Prompting — combine text, images, and audio in one prompt preview

Prompt template

Analyze the following content and answer the question.

Image 1: {image_1_description_or_url}
Image 2: {image_2_description_or_url}
Audio transcript: {audio_transcript}
Text context: {text_context}

Question: {question}

Answer using evidence from all provided modalities. Cite which modality supports each claim.

How to use

  1. 1Identify all modalities needed for the task
  2. 2Upload images/audio with clear labels
  3. 3Provide text descriptions as fallback for each modality
  4. 4Instruct the model to cross-reference modalities
  5. 5Require citations to specific modality in answers

Pro tips

  • Always provide text descriptions alongside images for reliability
  • Use high-resolution images for OCR and detail extraction
  • Label each modality clearly (Image 1, Audio, Text)
  • Ask the model to note contradictions between modalities

Works best with

ChatGPTClaude

Ratings & Reviews

Loading reviews…

Share your experience

Select a rating

Related Skills

Persona Prompting — get consistent, expert-toned answers
Prompting

Persona Prompting — get consistent, expert-toned answers

Give the AI a role, audience and constraints so every answer comes back in a consistent, professional voice.

PromptingWritingchatgpt
4.7
RAG Prompting — retrieval-augmented generation for grounded answers
Prompting

RAG Prompting — retrieval-augmented generation for grounded answers

Combine retrieved context with targeted prompts so the AI answers from your documents instead of hallucinating.

RAGRetrievalGrounding
4.5
Structured Output Prompting — reliable JSON, XML, and table extraction
Prompting

Structured Output Prompting — reliable JSON, XML, and table extraction

Force the AI to output in a strict schema using explicit format instructions, examples, and validation rules.

JSONStructured OutputParsing
3.9