What does extracting audio from a video cost by API?
Sume audio detach is $0.01 per job with no provider inference. Timeline audio is also $0.01 flat. Confirm the rate in GET /v1/catalog.
Audio detach is $0.01 per job on Sume's public rate. The docs give it as a per-job price, run on worker ffmpeg with no provider inference; confirm the live value in GET /v1/catalog. Timeline audio (concat or split) is also $0.01 flat per job.
What does a batch cost?
Multiply jobs by one cent. This is arithmetic on the per-job rate in the Audio detach docs, not a separate price list.
| Scenario | Jobs | Fee |
|---|---|---|
| One video, whole track | 1 | $0.01 |
| A 30-minute video in two ranges | 2 | $0.02 |
| 100 videos, one detach each | 100 | $1.00 |
| Detach once, then split into 12 ranges | 1 + 1 | $0.02 |
Does the format or range change the price?
The docs list one rate: $0.01 per job. format (wav or mp3 at 128 kbps), range, channels and sample_rate are options on that job, and the docs attach no extra charge to them.
What about the video render?
A Timeline 1.0 render is priced separately: $0.10 per ceil(output minute) in the Timeline docs, with an unbilled /plan preflight that reports estimated_cost_usd_micros.
Where do I confirm a price?
Sume's docs name GET /v1/catalog as the live check for both audio jobs.
curl https://api.sume.com/v1/catalog \
-H "Authorization: Bearer $SUME_API_KEY"How does the job run?
Audio detach defaults to mode: "async". Pass mode: "sync" to wait up to 30 seconds for a 200 finished job, or you get 202 and poll GET /v1/jobs/:id/status and GET /v1/jobs/:id/result. There is no GET /v1/audio-detach/:id. Idempotency-Key is required. The result is kind: audio_detach with audio_url, duration_seconds, format, channels and sample_rate; sample_rate is null when you omitted it and the source rate was inherited. The docs give the fee per job.
Detach is not clip inspection. For probing, stills or transcripts use video inspect; for a new MP4 cut use video trim, described in the Audio detach docs.
Sources
Related posts
More in Pricing
- Descript jump cut smoothing cost vs Sume flat edit rates
Descript prices smoothing at 0.5 AI credits per second of audio and 1.0 per second of video. Sume's edit steps are flat per job or per output minute.
- Do API price changes affect jobs already submitted? Sume
On Sume, the estimate is reserved when the request is accepted, then captured on success or refunded on failure. Here is how to read it in Usage.
- Eleven v4 TTS on Runway: 2.2 credits per 1,000 chars, then 5
Runway prices eleven_v4 at 2.2 credits per 1,000 characters until October 12, 2026 PT, then 5. Check a long script's cost on Sume before submit.
- ElevenLabs Music API price: $0.15 per minute, per track
ElevenLabs lists Music at $0.15 per minute generated. Convert it to a per-track budget, and see why Sume's flat per-generation price is not per minute.
Written by Sume