falText to jsonComing soon

fal-ai/ffmpeg-api/loudnorm

fal-ai/ffmpeg-api/loudnorm is a text to json tool from fal that runs in the background and returns audio and structured JSON. 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
audio, json
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

FieldKindDefaultDescription
audio_url requiredURL or file—URL of the audio file to normalize
integrated_loudnessnumber
-70 to -5
-18Integrated loudness target in LUFS.
true_peaknumber
-9 to 0
-0.1Maximum true peak in dBTP.
loudness_rangenumber
1 to 20
7Loudness range target in LU
offsetnumber
-99 to 99
0Offset gain in dB applied before the true-peak limiter
lineartrue or falsefalseUse linear normalization mode (single-pass). If false, uses dynamic mode (two-pass for better quality).
dual_monotrue or falsefalseTreat mono input files as dual-mono for correct EBU R128 measurement on stereo systems
print_summarytrue or falsefalseReturn loudness measurement summary with the normalized audio
measured_inumber
-99 to 0
—Measured integrated loudness of input file in LUFS. Required for linear mode.
measured_lranumber
0 to 99
—Measured loudness range of input file in LU. Required for linear mode.
measured_tpnumber
-99 to 99
—Measured true peak of input file in dBTP. Required for linear mode.
measured_threshnumber
-99 to 0
—Measured threshold of input file in LUFS. Required for linear mode.

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": "fal",
    "model": "fal-ai/ffmpeg-api/loudnorm",
    "input": {
      "audio_url": "https://storage.googleapis.com/falserverless/example_inputs/ffmpeg-audio.wav"
    }
  }'