Sonilo Video Analysis API

Reads a video and writes a timed creative brief, with a prompt per scene for music and sound design, ready to drive a later generation.

SoniloVideo GenerationProprietary EndpointNew

About Sonilo Video Analysis

Reads a video and writes a timed creative brief, with a prompt per scene for music and sound design, ready to drive a later generation.

videomultimodalscene analysis

Sonilo Video Analysis specs

Model ID
sonilo-video-analysis
Author
Sonilo
Category
Video Generation
Released
-
Input
TextVideo
Output
Text
Endpoints
POST/v1/chat/completions
Alternate model IDs
sonilo/sonilo-video-analysis

Sonilo Video Analysis API pricing

Live pay-as-you-go rates from the EmpirioLabs catalog. You are billed only for what you use, with no monthly minimum.

Type
Spec
Rate
Video analysis
per second
$0.0004
Compare on the full pricing page

How to call the Sonilo Video Analysis API

Sonilo Video Analysis serves the OpenAI-compatible Chat Completions API. Point any OpenAI SDK at https://api.empiriolabs.ai/v1 with your EmpirioLabs API key and use the model id sonilo-video-analysis. Get an API key from the EmpirioLabs dashboard.

cURL
curl https://api.empiriolabs.ai/v1/chat/completions \
  -H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "sonilo-video-analysis",
    "messages": [
      {"role": "user", "content": "Write a haiku about the ocean."}
    ]
  }'
Python (OpenAI SDK)
from openai import OpenAI

client = OpenAI(
    base_url="https://api.empiriolabs.ai/v1",
    api_key="YOUR_EMPIRIOLABS_API_KEY",
)

response = client.chat.completions.create(
    model="sonilo-video-analysis",
    messages=[{"role": "user", "content": "Write a haiku about the ocean."}],
)
print(response.choices[0].message.content)
Full Sonilo Video Analysis API reference

Sonilo Video Analysis API parameters

Request parameters supported by the Sonilo Video Analysis API on EmpirioLabs. Defaults apply when a field is omitted.

ParameterTypeDefaultRange / valuesDescription
modeenumbothboth, music, sfxWhich brief to write: a music direction, a sound design direction, or both. All three cost the same.
promptstring--Creative direction for the brief. Steers the music plan; the sound design plan follows the footage.
variants_numnumber11 to 5How many alternative creative briefs to write. Each variant is billed separately.
video_urlstring--Source video to analyse, as a publicly reachable URL. Up to 300MB and 8 minutes.

Good to know

Output

Returns a written creative brief as JSON, not generated media: a time-aligned segment plan with a prompt per segment, plus one overall prompt per requested variant. Use it to direct a later music or sound effects generation.

Controls

Supports source video, creative direction, a mode selecting the music brief, the sound design brief, or both, and 1 to 5 variants.

Limits

  • Source video up to 300MB and 8 minutes
  • In both mode the sound design prompt is authored once regardless of the variant count

Billing

  • Charged per second of source video at the catalog rate, with a 10 second minimum
  • Each variant is billed separately
  • A request rejected before generation is not billed.

Sonilo Video Analysis API: common questions

How much does the Sonilo Video Analysis API cost?

On EmpirioLabs, Sonilo Video Analysis is billed pay as you go: Video analysis $0.0004 per second. The live rate card on this page always matches what the API charges.

Is the Sonilo Video Analysis API OpenAI-compatible?

Yes. Sonilo Video Analysis serves the OpenAI-compatible Chat Completions API, so existing OpenAI SDKs work by pointing base_url at https://api.empiriolabs.ai/v1 and setting the model id to sonilo-video-analysis.

Can I try Sonilo Video Analysis in the browser before integrating?

Yes. The EmpirioLabs playground runs Sonilo Video Analysis in the browser with the same parameters the API exposes, so you can test prompts before writing code.

How do I get a Sonilo Video Analysis API key?

Create an EmpirioLabs account, then generate a key under API Keys in the dashboard. Billing is pay-as-you-go credits, so you only pay for the requests you make.

Ready to use better endpoints?

Check out our pricing or reach out if you want your own model deployed on our stack.