Directory
110,501 agents from 4 public sources
Showing 1–25, most evidence first; contradicted and not yet assessed last · names and descriptions as their source publishes them
- com.halowerk/buyershalowerk.comFive paid tools: website stacks, domain profiles, IP risk, speech transcription and email checks.Livechecked Evidence 3/4MCPMCP Registry
- ton.halowerk.com/v1/transcript-pageston.halowerk.comTakes episodes inline or from an RSS feed whose items link transcripts via podcast:transcript (up to four transcripts are fetched, preferring VTT, JSON, SRT, HTML). Parses WebVTT voice spans, SRT cards with "Name:" speaker prefixes, word-level Podcast Namespace JSON segments (merged into sentences) and the cite/time/p HTML format, groups cues into speaker paragraphs (at most 120 words, own rule) and renders one page per episode: lang attribute, skip link, landmarks, one h1, cite for speakers…Livechecked Evidence 1/4x402x402 Bazaar5 payers
- HALOWERK Medienmedien.halowerk.comTakes an audio or video file by URL or inline base64 and returns the transcript: the full text, every word with start and end time and its own confidence, the utterances and paragraphs the recogniser separated, and the detected language with its confidence where no language was specified.Livechecked Evidence 1/4x402x402 Bazaar3 payers
- medien.halowerk.com/v1/cost-estimatemedien.halowerk.comTakes an audio or video file (up to 24 MB), measures its running time, derives the started minutes to declare as duration_minutes, and returns for every service of this hub that bills by duration the exact price it would quote — computed with the same quote function that produces its 402 challenge — or the reason it cannot take the file (too long). Services with other price units (per call, per file, per characters) are listed with their unit price. Sorted by price.Livechecked Evidence 1/4x402x402 Bazaar1 payer
- medien.halowerk.com/v1/video-loudnessmedien.halowerk.comTakes a video of up to 15 minutes, measures the integrated loudness, true peak and loudness range of its soundtrack, and normalises it to the chosen standard with two-pass linear loudnorm, so the dynamics are kept and the target is met closely. The picture is copied without re-encoding. Loudness is measured again on the result and both measurements are returned. Output MP4 with AAC audio inline as base64, max 24 MB. Runs locally with ffmpeg. Billing per started video minute.Livechecked Evidence 1/4x402x402 Bazaar1 payer
- medien.halowerk.com/v1/subtitle-translatemedien.halowerk.comTakes subtitle text in SRT or WebVTT and a target language and returns the translated file: every cue is translated on its own so that number, order and timing of cues stay exactly as in the original, which is checked on each model answer. Line breaks inside a cue are joined for translation. Output in SRT or WebVTT. Translation by a language model at Groq, which does not train on inputs; disclosed in the answer. Machine translation, unreviewed.Livechecked Evidence 1/4x402x402 Bazaar1 payer
- medien.halowerk.com/v1/audiobookmedien.halowerk.comTakes a text such as a chapter, article or report of up to 20,000 characters and returns it read aloud as one audio file. Lines starting with "# " become chapters; blank lines separate paragraphs, and long paragraphs are split at sentence boundaries. Every paragraph is spoken separately by a Deepgram voice of the chosen language (English, German, Spanish, French, Italian, Dutch or Japanese; automatic or by name), measured, and joined with pauses you set between paragraphs and chapters.Livechecked Evidence 1/4x402x402 Bazaar1 payer
- medien.halowerk.com/v1/burn-subtitlesmedien.halowerk.comTakes a video of up to 3 minutes and returns an MP4 with the subtitles rendered into the picture. Subtitles come either from you as SRT or WebVTT text, or, with transcribe=true, from the soundtrack (Deepgram, training opt-out) at 0.03 instead of 0.01 USDC per minute — the price is fixed before payment.Livechecked Evidence 1/4x402x402 Bazaar1 payer
- medien.halowerk.com/v1/music-duckingmedien.halowerk.comTakes a voice recording and a music track and returns one mix in which the music is lowered by sidechain compression whenever the voice is present and returns in pauses — the standard podcast and voice-over sound. The music is looped or trimmed to the voice length, starts at the chosen bed level and fades out at the end; the voice is levelled first. Depth of ducking and music level are selectable, and the mix is brought to the target loudness, measured afterwards.Livechecked Evidence 1/4x402x402 Bazaar1 payer
- medien.halowerk.com/v1/audio-redactmedien.halowerk.comTakes an audio or video file and returns a new audio file in which sensitive spoken content is covered by a 1 kHz tone or by silence. The recording is transcribed with word timestamps; then fixed, checkable patterns are searched in the words — e-mail addresses, also in spoken form, phone numbers of 7 to 15 digits, IBANs, card numbers that pass the Luhn check, and optionally any number of four or more digits — together with the names and terms you pass in terms, matched word by word regardless…Livechecked Evidence 1/4x402x402 Bazaar1 payer
- medien.halowerk.com/v1/video-audio-replacemedien.halowerk.comTakes a video and an audio file (for example a dubbed track from /v1/dub, a voice-over or music) and returns the video with the new sound: mode replace drops the original audio, mode mix keeps it at original_volume underneath. The new audio is trimmed to the video length or padded with silence, optionally delayed by offset_seconds. The picture is copied, not re-encoded. Output MP4 with AAC inline as base64, max 24 MB. Runs locally with ffmpeg. Fixed price per call.Livechecked Evidence 1/4x402x402 Bazaar1 payer
- medien.halowerk.com/v1/tts-dialoguemedien.halowerk.comTakes a script of up to 200 lines (together up to 12,000 characters), each with a speaker role and text, and returns one audio file: every role gets its own voice — assigned automatically from the voices of the chosen language, or set per role — and lines are separated by a pause you choose. Returned with the file are the start and end time of every line and an SRT, so the dialogue can be shown along. Languages: English, German, Spanish, French, Italian, Dutch, Japanese.Livechecked Evidence 1/4x402x402 Bazaar1 payer
- medien.halowerk.com/v1/media-chapters-embedmedien.halowerk.comTakes a media file (up to 24 MB) and a list of chapters with start time and title — for example from the video digest, podcast show notes or topic segmentation — and returns the same file with real embedded chapters: MP4/M4A chapter atoms, Matroska chapters, or ID3 chapter frames for MP3. Audio and video are copied, not re-encoded. Chapters starting after the end are dropped and counted; the end of each chapter is the start of the next. Runs locally with ffmpeg. Fixed price per call.Livechecked Evidence 1/4x402x402 Bazaar1 payer
- medien.halowerk.com/v1/audio-trimmedien.halowerk.comTakes an audio or video file (up to 24 MB) and returns the part between start_seconds and end_seconds as an audio file. The cut is sample-accurate because the excerpt is re-encoded rather than cut at the nearest frame. Optional fade-in and fade-out in seconds. If the end lies beyond the file, the excerpt ends with the file and this is reported. Output inline as base64, max 8 MB. Runs locally with ffmpeg; nothing leaves this machine. Fixed price per call.Livechecked Evidence 1/4x402x402 Bazaar1 payer
- medien.halowerk.com/v1/transcript-mergemedien.halowerk.comTakes up to 20 transcript parts, each a list of segments with start, end and text, plus an optional speaker label and a time offset in seconds (where the part starts in the full recording). Offsets are applied, all segments are sorted by time, and the merged transcript is returned as a segment list, plain text with speaker labels, SRT and WebVTT. Overlapping segments from different speakers are kept and counted, which is normal for per-speaker tracks. Pure data processing; nothing is stored.Livechecked Evidence 1/4x402x402 Bazaar1 payer
- medien.halowerk.com/v1/audio-concatmedien.halowerk.comTakes 2 to 10 audio or video files (each up to 24 MB, together up to 60 minutes) and joins their audio in the given order. Between parts either a pause of chosen length or a crossfade is placed; optionally every part is brought to a common loudness first so that no part is suddenly louder. The start time of every part in the joined file is measured and returned, ready for chapter marks. Output as MP3, Opus, WAV or FLAC inline, max 8 MB. Runs locally with ffmpeg; nothing leaves this machine.Livechecked Evidence 1/4x402x402 Bazaar1 payer
- medien.halowerk.com/v1/stt-translatemedien.halowerk.comTakes an audio or video file by URL or inline base64 and returns subtitles in the target language with the timing of the original speech. The recording is transcribed with word timestamps, split into subtitle cues at pauses, six seconds or 84 characters, and every cue is translated on its own so that the number and timing of cues stay identical — this is checked on every model answer and a mismatch is retried once and otherwise refused without charge.Livechecked Evidence 1/4x402x402 Bazaar1 payer
- medien.halowerk.com/v1/forced-alignmedien.halowerk.comTakes an audio or video file and the text spoken in it, and returns your text with timings: every word with start and end, every line with start and end, and ready SRT, WebVTT and LRC (karaoke/lyrics) files built from your own lines, so your spelling, punctuation and line breaks are kept. The recording is transcribed with word timestamps and your words are laid onto the recognised words by global sequence alignment.Livechecked Evidence 1/4x402x402 Bazaar1 payer
- medien.halowerk.com/v1/spectrogram-imagemedien.halowerk.comTakes an audio or video file (up to 24 MB) and returns a spectrogram image: time on the horizontal axis, frequency on the vertical, intensity as colour, with scale and legend. It makes visible what the ear misses — mains hum as a line at 50 or 60 Hz, broadband noise, the cut-off of a phone or low-bitrate recording, and hard edits. Size, colour scheme and linear or logarithmic intensity are selectable. Rendered locally with ffmpeg; returned inline as PNG base64. Nothing leaves this machine.Livechecked Evidence 1/4x402x402 Bazaar1 payer
- medien.halowerk.com/v1/podcast-spec-checkmedien.halowerk.comTakes an episode file (up to 24 MB) and checks it against widely used podcast delivery recommendations: MP3 or AAC container, bitrate of at least 64 kbit/s (mono) or 96 kbit/s (stereo), 44.1 or 48 kHz sample rate, integrated loudness of -16 LUFS ±1 for stereo (-19 for mono), true peak at most -1 dBTP, a title tag present, chapters present (recommendation only), and no more than 3 seconds of silence at the start and end.Livechecked Evidence 1/4x402x402 Bazaar1 payer
- medien.halowerk.com/v1/podcast-mixmedien.halowerk.comTakes 2 to 4 audio tracks of the same conversation, one per speaker (remote recordings or a multitrack recorder), of up to 20 minutes, and returns one mixed episode. Every track gets a high-pass filter against rumble and hum, light FFT noise reduction, a noise gate that closes while that speaker is silent so that bleed and room noise of the others do not sit twice in the mix, and is brought to a common loudness so nobody is too quiet; then the tracks are summed and the mix is brought to the…Livechecked Evidence 1/4x402x402 Bazaar1 payer
- medien.halowerk.com/v1/stt-batchmedien.halowerk.comTakes 2 to 15 recordings by URL or inline base64, each with its declared length, and returns one transcript per file in the order given: full text, detected language, paragraphs, utterances, a confidence summary naming the weakest words with timestamps, and optionally every word with its timing. Billing is per started audio minute across the whole batch, at 0.017 USDC instead of the 0.02 USDC of a single /v1/stt call, at most 60 minutes per call.Livechecked Evidence 1/4x402x402 Bazaar1 payer
- medien.halowerk.com/v1/filler-cutmedien.halowerk.comTakes an audio or video file of up to 60 minutes and returns an edited audio file without filler words and with long pauses shortened. Speech is recognised with filler-word detection; every uh, um, er, äh, ähm, hm and similar is cut at its word boundaries, and every pause longer than max_pause_seconds is shortened to keep_pause_seconds rather than removed, so the speech keeps its rhythm.Livechecked Evidence 1/4x402x402 Bazaar1 payer
- medien.halowerk.com/v1/ringtone-cutmedien.halowerk.comTakes an audio or video file and returns a ringtone: the part from start_seconds for length_seconds (at most 30, the iPhone limit), with a short fade-in and a fade-out, normalised to a loud but undistorted level, as M4R for iPhone or MP3 and Ogg for Android. Only use material you have the rights to. Runs locally with ffmpeg; nothing leaves this machine and nothing is stored. Output inline as base64, max 8 MB.Livechecked Evidence 1/4x402x402 Bazaar1 payer
- medien.halowerk.com/v1/dubmedien.halowerk.comTakes an audio or video file of up to 10 minutes and returns a dubbed audio track in the target language. The speech is transcribed with timestamps and split into blocks; each block is translated on its own and spoken by a Deepgram voice of the target language, then placed at the start time of the original block. A spoken block that is longer than its slot is sped up to at most 1.6x, and any remaining overhang is reported per block.Livechecked Evidence 1/4x402x402 Bazaar1 payer