[GH-ISSUE #1354] Feature Request: Add Support for Audio/Video File Upload and image creating Processing #893

New issue

Closed

opened 2026-10-26 21:31:48 +00:00 by bsakaguchi · 3 comments

bsakaguchi commented

2026-10-26 21:31:48 +00:00

Owner

Originally created by @sakibahmedbayezid-max on GitHub (May 25, 2026).
Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-V3/issues/1354

Is your feature request related to a problem? Please describe.
Currently, DeepSeek can only process text input. I often have audio notes (MP3) and short video files that contain important information. Converting them to text manually using other tools (like Google Docs voice typing) is time-consuming and creates an extra, unnecessary step in my workflow.Maximum of time we use image fenerator now a days but gemini sti not have this feature.pleaae give this feature us like gemini

Describe the solution you'd like
I would like DeepSeek to have the ability to directly accept MP3, WAV, MP4, and similar audio/video file formats as input. The model should be able to process the audio stream or video frames to understand the content, generate transcripts, and answer questions based on the information within these files.when we give them a picture it can generate a picture design it edit it like gemini

Describe alternatives you've considered
As an alternative, I currently have to use a separate speech-to-text tool to manually transcribe the audio from these files. Then, I copy-paste that text to DeepSeek. This is an inefficient and disruptive process.I also use gemini they work greatly like image genrating after some days we see they come with image to video generator which is available multiple ai app based on america. I need to chinese version too

Additional context
This feature is common in other AI tools like Gemini and ChatGPT. Adding it would make DeepSeek much more useful for tasks like summarizing voice memos, analyzing video content, or providing feedback on audio/video projects. It's a highly requested feature from the community and would greatly enhance the user experience.

feature request mp3 mp4 image generator

Originally created by @sakibahmedbayezid-max on GitHub (May 25, 2026). Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-V3/issues/1354 Is your feature request related to a problem? Please describe. Currently, DeepSeek can only process text input. I often have audio notes (MP3) and short video files that contain important information. Converting them to text manually using other tools (like Google Docs voice typing) is time-consuming and creates an extra, unnecessary step in my workflow.Maximum of time we use image fenerator now a days but gemini sti not have this feature.pleaae give this feature us like gemini Describe the solution you'd like I would like DeepSeek to have the ability to directly accept MP3, WAV, MP4, and similar audio/video file formats as input. The model should be able to process the audio stream or video frames to understand the content, generate transcripts, and answer questions based on the information within these files.when we give them a picture it can generate a picture design it edit it like gemini Describe alternatives you've considered As an alternative, I currently have to use a separate speech-to-text tool to manually transcribe the audio from these files. Then, I copy-paste that text to DeepSeek. This is an inefficient and disruptive process.I also use gemini they work greatly like image genrating after some days we see they come with image to video generator which is available multiple ai app based on america. I need to chinese version too Additional context This feature is common in other AI tools like Gemini and ChatGPT. Adding it would make DeepSeek much more useful for tasks like summarizing voice memos, analyzing video content, or providing feedback on audio/video projects. It's a highly requested feature from the community and would greatly enhance the user experience. ### feature request mp3 mp4 image generator

bsakaguchi

2026-10-26 21:31:48 +00:00

closed this issue
added the
stale

closed-as-stale
labels

bsakaguchi commented

2026-10-26 21:31:49 +00:00

Author

Owner

@qingkong66 commented on GitHub (May 25, 2026):

@sakibahmedbayezid-max

Thanks for the request.

Current status:

Image upload: supported (Vision tab)
Audio/video upload: not supported
Image generation: not supported (DeepSeek is a text model, not multimodal generation)

Audio/video transcription would require additional multimodal infrastructure. No timeline from the team.

Your request is on record.

@qingkong66 commented on GitHub (May 25, 2026): @sakibahmedbayezid-max Thanks for the request. Current status: - Image upload: supported (Vision tab) - Audio/video upload: not supported - Image generation: not supported (DeepSeek is a text model, not multimodal generation) Audio/video transcription would require additional multimodal infrastructure. No timeline from the team. Your request is on record.

bsakaguchi commented

2026-10-26 21:31:50 +00:00

Author

Owner

@github-actions[bot] commented on GitHub (Jul 5, 2026):

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. If you believe this issue is still relevant, please leave a comment to keep it open. Thank you for your contributions!

@github-actions[bot] commented on GitHub (Jul 5, 2026): This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. If you believe this issue is still relevant, please leave a comment to keep it open. Thank you for your contributions!

bsakaguchi commented

2026-10-26 21:31:50 +00:00

Author

Owner

@github-actions[bot] commented on GitHub (Aug 1, 2026):

false

@github-actions[bot] commented on GitHub (Aug 1, 2026): false