Multimodal
Universal Extractor
All-in-one extractor for image, video, audio, and documents: auto-detects modality and applies the right pipeline.
Note: This playground provides simulated output to showcase functionality. No input data is processed or stored on our servers. Use this demo to explore the feature extractor's capabilities before integrating it into your application.
Input
Enter the text you want to process
Output
{
"universal_extractor_v1_embedding": "Gemini Embedding 2 vector (3072-d) for the content.",
"modality": "Detected modality: image, video, audio, or document.",
"text": "Extracted text (OCR, transcription, or document text).",
"description": "AI-generated description of the content.",
"segment_index": "Segment index (for chunked content like video/audio/documents).",
"segment_total": "Total segments for this source object.",
"page_number": "Page number (documents only).",
"start_time_s": "Segment start time in seconds (video/audio only).",
"end_time_s": "Segment end time in seconds (video/audio only).",
"duration_s": "Total file duration in seconds (video/audio only)."
}Ready to run Universal Extractor on your data? Spin it up in Studio: no infra to host.
Run this in StudioUniversal Extractor: common questions
- How much does the Universal All-in-One (Gemini) extractor cost?
- 15 cr/image. Credits are billed per unit processed; see mixpeek.com/pricing for the credit rate.
- What file types does Universal All-in-One (Gemini) support?
- Image, Video, Audio, PDF, Text. It produces embeddings from gemini-embedding-2.
Already have embeddings? Skip extraction: search your own vectors with MVS, from $25/mo for up to 1M vectors.
Try MVS →