Make videos on the computer you already own. FreeVideo runs MiniMax H3 in as little as 8 GB of VRAM and 16 GB of RAM, and adapts its acceleration path to your hardware.
Agent: tool descriptions say it generates videos
Bowen Xue56b8ffc75546
diff --git a/freevideo_engine/agent/mcp.py b/freevideo_engine/agent/mcp.pyindex a003728..3b672c2 100644--- a/freevideo_engine/agent/mcp.py+++ b/freevideo_engine/agent/mcp.py@@ -22,7 +22,7 @@ import timefrom .client import ApiError, Client, DONEPROTOCOLS = ('2025-06-18', '2025-03-26', '2024-11-05')-INSTRUCTIONS = """FreeVideo generates videos with synchronized audio (MiniMax H3) on this computer's GPU.+INSTRUCTIONS = """FreeVideo generates videos (MiniMax H3) on this computer's GPU.Start with freevideo_status and freevideo_capabilities. Write prompts as the guide says (freevideo_prompt_guide): English sectionsintegrated_multimodal_description / overall_soundscape / non_diegetic_music, [Shot N] cuts, (S1) <d>[Language] ...</d>dialogue. Generation uses continuous chains and takes minutes: submit, then call freevideo_wait (at most 25 seconds)@@ -44,7 +44,7 @@ def tool_list():dict(name='freevideo_prompt_guide', title='H3 prompt guide', description='How to write prompts: sections, shots and cuts, camera motion, dialogue, references, short-drama tips, and a full example.', annotations=read),dict(name='freevideo_schema', title='Job JSON Schemas', description='JSON Schemas of every job kind and of image edit recipes.', annotations=read),dict(name='freevideo_plan', title='Plan a job', description="Validate a job without running it: actual frames/seconds, sampling passes, warnings and a time estimate from this computer's history. Same fields as freevideo_generate.", annotations=read),- dict(name='freevideo_generate', title='Generate a video', description='Generate one video with audio from an H3 prompt, up to 60 seconds: a longer request continues and joins into one file automatically. Prefer a new shot with its reference pictures wherever the film can cut; continue only a take, action or sound that must stay unbroken. Use this for any single video, also after freevideo_enhance_prompt; the drama tools are only for a film of several separately chosen shots. Optionally from first/last frames or references (files, local paths, or frames of earlier jobs). Returns the job; with wait, its result (video path and URL).', annotations=write),+ dict(name='freevideo_generate', title='Generate a video', description='Generate one video from an H3 prompt, up to 60 seconds: a longer request continues and joins into one file automatically. Prefer a new shot with its reference pictures wherever the film can cut; continue only a take, action or sound that must stay unbroken. Use this for any single video, also after freevideo_enhance_prompt; the drama tools are only for a film of several separately chosen shots. Optionally from first/last frames or references (files, local paths, or frames of earlier jobs). Returns the job; with wait, its result (video path and URL).', annotations=write),dict(name='freevideo_submit_batch', title='Submit a storyboard', description='Submit several jobs at once. Each row is a job object with "kind" (generate default, assemble, vlm, enhance) and an optional "ref"; later rows use "@ref" wherever a job id is expected (from_job, after, clips, refine_from). FreeVideo runs them in dependency order.', annotations=write),dict(name='freevideo_job', title='Job status', description='Status, progress, result or error of a job.', annotations=read),dict(name='freevideo_wait', title='Wait for a job or the user', description="Wait at most 25 seconds for a job (with id) or, without id, for the user's words in this session. Returns early when the user says something (inbox). If the job is still active, call it again with the same ID; do not resubmit.", annotations=read),diff --git a/freevideo_engine/agent/routes.py b/freevideo_engine/agent/routes.pyindex a0bd8d4..aee2b25 100644--- a/freevideo_engine/agent/routes.py+++ b/freevideo_engine/agent/routes.py@@ -186,7 +186,7 @@ def capabilities(port, jobs):features=features(continuation, vlm),device=dict(backend=machine.get('device_backend', 'cuda') if machine else None,vram_limit_gib=machine.get('vram_gib'), ram_limit_gib=machine.get('ram_gib')),- kinds={'generate': 'Video with audio from a prompt and optional keyframes or references',+ kinds={'generate': 'Video from a prompt and optional keyframes or references','assemble': 'Join finished clips into one video (cut or crossfade)','vlm': 'Ask the local vision-language model about images or sampled video frames','enhance': 'Rewrite a rough idea into a full H3 prompt with the local VLM',