Model API

LTX-2.3 22B

Generate video with audio from text using LTX-2.3

Model id

Use this in every request

ltx-2.3-22b/text-to-video

This model has other modes with their own ids: ltx-2.3-22b/image-to-video.

Run it

Quote the input, start the generation with the quote, then poll the job. Set RAYWAKE_API_KEY first; see Authentication.

# 1. Price the exact input (quotes are valid for up to 10 minutes)
curl -s https://api.raywake.com/v1/quotes \
  -H "Authorization: Bearer $RAYWAKE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "ltx-2.3-22b/text-to-video",
  "input": {
    "prompt": "A red ceramic cup on a wooden table, soft morning light"
  }
}'

# 2. Start the generation with the quote_id from step 1
curl -s https://api.raywake.com/v1/generate \
  -H "Authorization: Bearer $RAYWAKE_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{"model": "ltx-2.3-22b/text-to-video", "quote_id": "QUOTE_ID", "input": {"prompt":"A red ceramic cup on a wooden table, soft morning light"}}'

# 3. Poll until the status is terminal
curl -s https://api.raywake.com/v1/jobs/JOB_ID \
  -H "Authorization: Bearer $RAYWAKE_API_KEY"

Input

Input fields for ltx-2.3-22b/text-to-video
Name	Type	Description
`prompt`required	string	The prompt to generate the video from.
`num_frames`	integer	The number of frames to generate. Default: `121`
`video_size`	string (enum)	The size of the generated video. Default: `landscape_16_9` One of: `square_hd`, `square`, `portrait_4_3`, `portrait_16_9`, `landscape_4_3`, `landscape_16_9`
`generate_audio`	boolean	Whether to generate audio for the video. Default: `true`
`use_multiscale`	boolean	Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details. Default: `true`
`fps`	number (enum)	The frames per second of the generated video. Default: `24` One of: `24`
`num_inference_steps`	integer	The number of inference steps to use. Default: `40`
`video_cfg_scale`	number	The Classifier-Free Guidance (CFG) scale for the video. Higher values result in more consistent and focused video content. Default: `3`
`video_stg_scale`	number	The Spatiotemporal Guidance (STG) scale for the video. Higher values result in more consistent and focused video content. Default: `0`
`video_rescaling_scale`	number	The rescaling scale for the video. Controls the ratio between classifier-free guidance and spatiotemporal guidance. Default: `0.7`
`video_modality_scale`	number	The modality scale for the video. Controls the ratio between video and audio modalities. Default: `3`
`audio_cfg_scale`	number	The Classifier-Free Guidance (CFG) scale for the audio. Higher values result in more consistent and focused audio content. Default: `7`
`audio_stg_scale`	number	The Spatiotemporal Guidance (STG) scale for the audio. Higher values result in more consistent and focused audio content. Default: `0`
`audio_rescaling_scale`	number	The rescaling scale for the audio. Controls the ratio between classifier-free guidance and spatiotemporal guidance. Default: `0.7`
`audio_modality_scale`	number	The modality scale for the audio. Controls the ratio between video and audio modalities. Default: `3`
`gradient_estimation_gamma`	number	The gamma of gradient estimation during denoising. Set to 0 to disable. Default: `2`
`use_restart_sampling`	boolean	Whether to use restart sampling. This will inject a small amount of noise during each denoising step, which can help improve the quality of the generated video. Default: `false`
`scheduler`	string (enum)	The scheduler to use. Default: `ltx2` One of: `ltx2`, `linear_quadratic`, `beta`
`acceleration`	string (enum)	The acceleration level to use. Default: `regular` One of: `none`, `regular`, `high`, `full`
`camera_lora`	string (enum)	The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera. Default: `none` One of: `none`
`camera_lora_scale`	number (enum)	The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera. Default: `1` One of: `1`
`negative_prompt`	string	The negative prompt to generate the video from. Default: `news broadcast, 3d animation, computer graphics, pc game, console game, video game, cartoon, childish, watermark, logo, text, on screen text, subtitles, titles, signature, slowmo, static`
`seed`	integer	The seed for the random number generator.
`enable_prompt_expansion`	boolean	Whether to enable prompt expansion. Default: `true`
`video_output_type`	string (enum)	The output type of the generated video. Default: `X264 (.mp4)` One of: `X264 (.mp4)`, `VP9 (.webm)`, `PRORES4444 (.mov)`, `GIF (.gif)`
`video_quality`	string (enum)	The quality of the generated video. Default: `high` One of: `high`
`video_write_mode`	string (enum)	The write mode of the generated video. Default: `balanced` One of: `fast`, `balanced`, `small`
`sync_mode`	boolean	If `True`, the media will be returned as a data URI and the output data won't be available in the request history. Default: `false`
`distill_lora_first_pass_scale`	number	The scale of the distill LoRA to use for the first pass. Set to 0 to disable. Default: `0.2`
`distill_lora_second_pass_scale`	number	The scale of the distill LoRA to use for the second and subsequent passes. Default: `0.5`

Output

A succeeded job lists its results under outputs, stored on our side. See Jobs for every field.

Job excerpt

"outputs": [
  { "type": "video", "url": "https://…", "mime_type": "video/mp4", "thumbnail_url": "https://…" }
]

Pricing

1 megapixel$0.01/ megapixel

The exact charge for your input comes from a quote. How charges settle