FastVideo / Fast-H3
Fast-H3
FastH3 is a four-forward distilled MiniMax H3 model that generates synchronized video and stereo audio from a text prompt. This H200-backed Preview v1 checkpoint supports native 5.167–14.375 second T2AV clips at 24 FPS; FL2VA and Ref2VA were not distilled.
Overview
FastH3 is FastVideo's distilled version of MiniMax H3 for text-to-audio-video generation. From one written prompt, it creates a landscape video with matching visuals and synchronized audio, including ambience, sound effects, music, and spoken dialogue. The preview checkpoint uses four transformer forward passes to reduce generation cost while preserving the MiniMax H3 audio-video workflow.
What you can build
- Short cinematic scenes with spoken dialogue
- Product and campaign videos with matching sound design
- Character moments with environmental ambience and voice
- Social clips, concept shots, trailers, and visual story beats
- Nature, city, action, and atmosphere footage with synchronized effects
Inputs
- Prompt: Describe the subject, action, setting, camera movement, lighting, visual style, ambience, sound effects, and dialogue. Put the exact words to be spoken in quotation marks and identify the speaker.
- Duration: Choose a whole-number duration from 5 to 15 seconds. FastH3 uses a causal video frame grid, so the generated clip length is the nearest supported native duration rather than an exact wall-clock match.
- Seed: Optionally set a seed from 0 to 4294967295 for repeatable iterations.
Outputs
The model returns one MP4 containing both video and audio.
- Resolution: 1344 × 768 landscape
- Frame rate: 24 FPS
- Video codec: H.264
- Audio codec: AAC
- Audio can include synchronized speech, ambience, music, and effects requested in the prompt
Recommended settings
- Start with a 5- or 6-second clip while refining composition and motion.
- Describe one clear primary action and keep the camera direction explicit.
- For speech, name the speaker, put the line in quotation marks, and specify language, tone, and delivery.
- Describe background sound separately from dialogue so both are represented.
- Keep the same seed when comparing prompt changes, then change it to explore a new composition.
Limitations
- This FastH3 Preview v1 checkpoint supports text-to-audio-video only. It does not support image-to-video, first-frame conditioning, or reference-video input.
- Duration choices are mapped to supported native frame counts. The 15-second option maps to the checkpoint maximum of 345 frames, or approximately 14.375 seconds at 24 FPS.
- Lip synchronization, exact wording, character identity, fine text, and complex physical interactions can vary between generations.
- The current integration uses a fixed landscape output size; portrait and custom aspect ratios are not exposed.
- Generation is compute-intensive and processing time varies with worker availability.
Model and license notes
FastH3 is published by FastVideo and is based on MiniMax H3. Review the checkpoint's model card and license terms before using generated media in production or commercial workflows.
Example prompts
Great starting points for Fast-H3.
API quick start
Run Fast-H3 with a single API call.
{
"prompt": "A woman on a stormy pier turns toward the…",
"duration": 5,
"resolution": "480P",
"ratio": "16:9"
}