Model API
MiniMax H3 Text to video Turbo API
MiniMax H3 Text to video Turbo API on Phosor. Start with a written scene. Describe the subject, action, camera movement and setting. Explore API inputs, documentation and current pricing.
- API model ID
- minimax/h3/text-to-video/turbo
- Capabilities
- text-to-video
Browse model information and examples without an account. Sign in to generate.
When to use text to video
Explore an idea when you do not have a starting image.
Required inputs: A text prompt.
This is the Turbo variant. A Standard option is also available for this input mode. Compare your own outputs and current rates when choosing.
Compare all MiniMax H3 modes →API inputs and controls
prompt
Set resolution_tier, aspect_ratio and duration to control the output. The playground shows current supported choices and reference limits.
See the complete parameter reference and request examples before integrating.
MiniMax H3 Text to video Turbo API request example
Set PHOSOR_API_KEY to your API key, then submit this request from your terminal. Generation is billed at current rates.
curl -X POST https://phosor.ai/api/v1/inference/submit \
-H "X-API-Key: $PHOSOR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "minimax/h3/text-to-video/turbo",
"prompt": "A hiker crosses a snowy mountain ridge at sunrise; wide shot, slow tracking camera.",
"duration": 5,
"resolution_tier": "480p",
"aspect_ratio": "16:9"
}'The response includes a request_id. Use it to check request status and retrieve the video result. See the API reference for all supported controls.
API access
Use minimax/h3/text-to-video/turbo as the model ID in your API request. Authenticate with an X-API-Key header, submit your request, then check its status and retrieve the result.
See current pricing for output and reference input charges.
Explore more models
- MiniMax H3 Image to video
MiniMax H3 Image to video API on Phosor. Animate a starting image and describe the motion. Add an optional ending image for first and last frame control. Explore API inputs, documentation and current pricing.
- MiniMax H3 Text to video
MiniMax H3 Text to video API on Phosor. Start with a written scene. Describe the subject, action, camera movement and setting. Explore API inputs, documentation and current pricing.
- MiniMax H3 Reference to video
MiniMax H3 Reference to video API on Phosor. Guide a clip with reference images or videos, with optional audio references. Address uploaded references in your prompt using <Picture n>, <Video n> and <Audio n>. Explore API inputs, documentation and current pricing.
- MiniMax H3 Image to video Turbo
MiniMax H3 Image to video Turbo API on Phosor. Animate a starting image and describe the motion. Add an optional ending image for first and last frame control. Explore API inputs, documentation and current pricing.
- MiniMax H3 Reference to video Turbo
MiniMax H3 Reference to video Turbo API on Phosor. Guide a clip with reference images or videos, with optional audio references. Address uploaded references in your prompt using <Picture n>, <Video n> and <Audio n>. Explore API inputs, documentation and current pricing.
- wan/v2.2-a14b/image-to-video
Transform any image into a dynamic video. High quality 14B parameter model with excellent motion generation.
- wan/v2.2-a14b/text-to-video
Generate videos from text descriptions. Create cinematic scenes with natural motion and high visual fidelity.
- wan/v2.2-a14b/image-to-video/lora
Apply your custom LoRA styles to image-to-video generation. Upload your trained LoRA and create stylized videos from any image.
- wan/v2.2-a14b/text-to-video/lora
Apply your custom LoRA styles to text-to-video generation. Upload your trained LoRA and create stylized videos from text prompts.
- wan/v2.2-a14b/image-to-video/turbo
Turbo I2V — 4-step LightX2V. ~5x faster than quality mode, ~5 seconds of video, 32 FPS. Great for rapid iteration.
- wan/v2.2-a14b/text-to-video/turbo
Turbo T2V — 4-step LightX2V. ~5x faster than quality mode, ~5 seconds of video, 32 FPS. Great for rapid iteration.
- qwen-image/v2512/text-to-image
Qwen Image 2512 — High quality text-to-image. 28-step generation, excellent detail, Chinese/English text rendering. Up to 1280×768.
- flux2/dev/text-to-image
FLUX.2-dev — High-resolution text-to-image with a 2048 long edge and six fixed aspect ratios.
- qwen-image/v2512/text-to-image/lora
Qwen Image 2512 + LoRA — Apply custom LoRA styles to high-quality text-to-image generation.
- z-image/turbo/text-to-image
Z-Image Turbo T2I — Ultra-fast 4-step text-to-image. Sub-second latency, perfect for rapid iteration.
- z-image/turbo/text-to-image/lora
Z-Image Turbo T2I + LoRA — Fast text-to-image with custom LoRA styles.
- z-image/turbo/image-to-image
Z-Image Turbo I2I — Fast image-to-image transformation. Style transfer, enhancement, creative modifications.
- flux2/dev/image-edit
FLUX.2-dev — Image Edit with the same 2048-long-edge resolution policy.
- z-image/turbo/image-to-image/lora
Z-Image Turbo I2I + LoRA — Image-to-image with custom LoRA styles.
- qwen-image/v2511/image-edit
Qwen Image Edit 2511 — Multi-reference image editing. Upload 1–3 reference images and describe the target scene. 28-step high-quality generation.
- wan/v2.2-a14b/speech-to-video
Speech to Video — Generate lip-synced video from an image and audio. Upload a portrait image and speech audio to create talking-head videos.
- wan/v2.2-a14b/animate
Animate — Bring images to life using a reference video for motion. Upload an image and a motion reference video to create animated content.
- ltx-video/v2.3/image-audio-to-video
LTX Video 2.3 - speech-driven video from an image and required audio track, with cinematic motion and synchronized audio.
- qwen3-tts/text-to-speech/1.7b
Qwen3-TTS CustomVoice — Text to Speech with 10 preset voices. Supports Chinese, English and Japanese. 1.7B parameter model with low-latency synthesis.
- openai/gpt-image-2/text-to-image
GPT Image 2 — Frontier text-to-image with exceptional prompt following and text rendering. 1024/1536 sizes.