HedraAudio to videoComing soon

ltx-2-5

Name: ltx-2-5
Brand: Hedra

ltx-2-5 is an audio to video tool from Hedra that runs in the background and returns video. Coming soon: listed with its price, not yet open to runs.

This tool is listed but not yet available to run.

Price pending

Pricing

Price pending.

Limits

Runs: In the background
Returns: video
Longest queue wait: 3600s
Run deadline: 1800s
Largest inline input: 1024 KB
Largest input file: 500 MB
Largest output: 4768 MB
Outputs per run: 16

Input

Field	Kind	Default	Description
`prompt` required	text	—	Generation prompt. From 1 to 5000 characters.
`resolution` required	one of 1080p, 720p, 1440p, 2160p	—	Output resolution.
`aspect_ratio` required	one of auto, 16:9, 9:16	—	Output aspect ratio.
`audio`	JSON	—	A file uploaded via POST /v3/files, referenced by the returned url.
`quality`	one of fast, pro	fast	Quality level to generate at. `fast` — tuned for turnaround, and the only level that renders 1440p, 2160p, or clips past 10 seconds. `pro` — the higher-fidelity tier, for final output at 720p or 1080p, and the level that caps both the clip it renders and the audio driving it at 10 seconds.
`end_image`	JSON	—	A file uploaded via POST /v3/files, referenced by the returned url.
`duration_ms`	one of 6000, 8000, 10000, 12000, 14000, 16000, 18000, 20000	—	Duration in ms.
`num_outputs`	one of 1	1	Number of outputs generated per job. Only 1 is supported.
`start_image`	JSON	—	A file uploaded via POST /v3/files, referenced by the returned url.
`generate_audio`	true or false	true	Whether to generate native audio for the video.

Same request in code

curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "hedra",
    "model": "ltx-2-5",
    "input": {
      "prompt": "<prompt>",
      "resolution": "1080p",
      "aspect_ratio": "auto"
    }
  }'