Discover

Captioned audio waveform video

● Live

halowerk.com

Copies a prompt for your agent.

The audio window (up to 60 s, any audio file or the audio track of a video) drives an ffmpeg 6.1 showwaves waveform (mode cline, line, p2p or point, square-root amplitude scale, mono mix) in a band across the middle of the frame. Captions come as a cue list or as WebVTT/SRT text (cue times refer to the original audio and are shifted by start_s; markup tags are removed), are wrapped by measured text width into at most three centred lines (Liberation Sans Bold) and shown with drawtext exactly…

Price
$0.02
Asked in its payment challenge
Chain
Base
Paid in
USDC
Live
4 of 4 checks

Endpoints

86 more endpoints · on x402 Bazaar

Checks and payment terms on this page refer to the first endpoint's example. Other endpoints have not been checked individually.

Base URLhttps://ton.halowerk.com/v1

  • POST/video-dup-detect$0.02Both videos (up to 300 s each) are sampled at sample_fps from their start, each sample is reduced to 64×64 grey and hashed with a 64-bit DCT perceptual hash (pHash method; aspect ratio ignored, so rescaling does not matter). Flat samples (standard deviation below 4 grey levels on the 32×32 image) carry no information and are skipped. Every time offset between the two sequences is tried; at each offset a pair of samples matches when their hashes differ in at most max_hamming bits.
    Example
    curl -i -X POST 'https://ton.halowerk.com/v1/video-dup-detect' \
      -H 'Content-Type: application/json' \
      -d '{"video_a_url":"https://upload.wikimedia.org/wikipedia/commons/2/2c/Rotating_earth_%28large%29.gif","video_b_url":"https://upload.wikimedia.org/wikipedia/commons/2/2c/Rotating_earth_%28large%29.gif"}'
  • POST/video-quality-compare$0.02Both videos are decoded from start_s for duration_s (at most 60 s), converted to 8-bit YUV 4:2:0 and aligned frame by frame at the frame rate of the reference; the distorted video is scaled to the reference size with a bicubic filter when the sizes differ (the display aspect ratios must agree within 2 %).
    Example
    curl -i -X POST 'https://ton.halowerk.com/v1/video-quality-compare' \
      -H 'Content-Type: application/json' \
      -d '{"worst_frames":3,"distorted_url":"https://upload.wikimedia.org/wikipedia/commons/2/2c/Rotating_earth_%28large%29.gif","reference_url":"https://upload.wikimedia.org/wikipedia/commons/2/2c/Rotating_earth_%28large%29.gif"}'
  • POST/video-stabilize$0.02Pass 1 runs ffmpeg 6.1 vidstabdetect (vid.stab 1.1, local motion fields), pass 2 vidstabtransform with the chosen smoothing window (frames), border handling (static optimal zoom, adaptive zoom, black or kept borders) or tripod mode, followed by a light unsharp mask as the vid.stab authors recommend, then H.264 (libx264, CRF by quality) with AAC audio.
    Example
    curl -i -X POST 'https://ton.halowerk.com/v1/video-stabilize' \
      -H 'Content-Type: application/json' \
      -d '{"smoothing":10,"video_url":"https://upload.wikimedia.org/wikipedia/commons/2/2c/Rotating_earth_%28large%29.gif"}'
  • POST/video-text-ocr$0.03Samples the video at sample_fps; only samples whose 160 px grey image differs from the last OCR frame (more than 0.3 % of pixels changing by more than 24 levels) are read again, at most max_ocr_frames per call (the largest changes win). The chosen frames are re-extracted at up to 1280 px width (small videos are upscaled 2x) and read with Tesseract 5.3.4 (LSTM, sparse-text mode, Ubuntu tessdata eng/deu, Apache-2.0).
    Example
    curl -i -X POST 'https://ton.halowerk.com/v1/video-text-ocr' \
      -H 'Content-Type: application/json' \
      -d '{"video_url":"https://upload.wikimedia.org/wikipedia/commons/2/2c/Rotating_earth_%28large%29.gif","max_ocr_frames":4}'
  • POST/voice-agent-eval$0.005Takes the turns of a voice-agent conversation (speaker, text, optional start/end times) and your goal criteria (required phrases per speaker, success and failure phrases). Without any language model it detects, with German and English phrase lists: agent fallback/no-match prompts, user requests for a human, agent transfers, user corrections, repeated user utterances and repeated agent prompts (normalised Levenshtein similarity >= 0.8 / 0.9), and with timestamps: response latency after each user…
    Example
    curl -i -X POST 'https://ton.halowerk.com/v1/voice-agent-eval' \
      -H 'Content-Type: application/json' \
      -d '{"goal":{"success_phrases":["ist gebucht"]},"turns":[{"text":"Guten Tag, wie kann ich helfen?","speaker":"agent"},{"text":"Ich möchte einen Termin am Freitag.","speaker":"user"},{"text":"Ihr Termin am Freitag um 10 Uhr ist gebucht.","speaker":"agent"}],"ended_by":"agent"}'

A dash means the listing gives no price or method. {Braces} mark a value you fill in. Copy buttons copy an example URL.

Showing 5 of 87 endpoints. First endpoints

Agents can find it through the Superstables MCP server and JSON API: GET /api/v1/services/ton.halowerk.com

Recent checks

13 Nov 2026Taller is slower; grey is not live.17 Nov 2026
Median response
520 ms
Last checked
17 Nov, 15:23 UTC

Our probes look for a payment challenge. They don't test payment or delivery.

All 4 checks
When (UTC)ResultHTTPResponse
17 Nov, 15:23 UTCLive402606ms
16 Nov, 03:24 UTCLive402375ms
14 Nov, 15:21 UTCLive402871ms
13 Nov, 00:24 UTCLive402434ms

Questions

Did our last probe detect a payment challenge?

At our last probe on 17 Nov, 15:23 UTC, it returned HTTP 402 or another detected payment-challenge signal.

What payment terms does ton.halowerk.com advertise?

The listing advertises x402, Base and USDC. It names cdp as its facilitator. Check the seller's current payment challenge and authentication requirements before paying.

Something wrong on this page? Tell us.