tidewell/media-transcriber
tidewell--media-transcriberDestructive
This tool calls the Actor "tidewell/media-transcriber" and retrieves its output results. Actor description: Returns a transcript per audio or video file: text, timestamped segments, detected language, SRT and VTT subtitles and optional word timestamps, with Whisper in 99 languages. Input: MP3, MP4, WAV and other media links, podcast RSS feeds or Apple Podcasts links. From $0.004 per audio minute.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "tidewell--media-transcriber"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| task | No | transcribe: text in the spoken language. translate: English translation of any language (Whisper's built-in speech translation). Example values: "transcribe" | transcribe |
| model | No | Bigger models are more accurate (names, accents, noisy audio, non-English) but slower and priced higher per minute. base is a good default for clear speech; small is noticeably better for most languages. Example values: "base" | base |
| language | No | Spoken language. Auto-detect works well; set it when you know it, which avoids rare detection mistakes on short or noisy clips. Codes such as en, es, de, fr, ja; the most-used languages are listed first. Example values: "auto" | auto |
| waitSecs | No | Max seconds (0–45, default 30) to cap the wait for the Actor run to reach terminal state. For long-running Actors the response returns at the cap with the current run status; follow `nextStep` to poll via get-actor-run. Set to 0 to fire-and-forget. | |
| mediaUrls | No | Direct links to audio or video files (MP3, M4A, WAV, FLAC, OGG, OPUS, AAC, MP4, MOV, WEBM, MKV and more), podcast RSS feeds, Apple Podcasts show or episode links, or web pages that embed an audio/video file. Google Drive and Dropbox share links work. YouTube, TikTok, Instagram, Spotify and similar platform pages are not supported. Example values: ["https://archive.org/download/life_poem_21_dickinson/life_21_dickinson_ad_64kb.mp3"] | |
| vadFilter | No | Silero voice activity detection skips silence and non-speech, which is faster and avoids made-up text in silent parts. Turn off only if quiet speech is being skipped. Example values: true | |
| httpHeaders | No | Headers sent with every download, e.g. {"Authorization": "Bearer ..."} for private file servers or private podcast feeds. | |
| initialPrompt | No | Names, jargon or spelling to steer the transcript, e.g. "Kubernetes, Grafana, Dr. Nkemelu". Keep it short. | |
| maxFileSizeMb | No | Files larger than this are skipped (not charged). Video files are large: about 1 GB per hour of HD video is common. Example values: 2000 | |
| uploadedFiles | No | Upload files from your computer. They are stored in a key-value store and transcribed like media URLs. | |
| wordTimestamps | No | Add every word with its start, end and confidence to the dataset row and the JSON file. Free (subtitles always use word timing internally). | |
| subtitleMaxLines | No | Maximum lines per subtitle cue. Example values: 2 | |
| episodeTitleFilter | No | Only episodes whose title contains this text (case-insensitive). Separate alternatives with |, e.g. "interview|Q&A". | |
| maxDurationMinutes | No | Transcribe at most the first N minutes of each file (you pay only for what is transcribed). Empty = whole file. | |
| maxEpisodesPerFeed | No | How many episodes to transcribe from each podcast feed, newest first, after the filters below. 0 = all matching episodes. Example values: 1 | |
| downloadTimeoutSecs | No | Maximum time to download one file. Example values: 900 | |
| subtitleMaxLineLength | No | Maximum characters per subtitle line in the SRT/VTT files. 42 is the broadcast standard. Example values: 42 | |
| episodesPublishedAfter | No | Only episodes published on or after this date: YYYY-MM-DD, or relative like "30 days" or "2 weeks". | |
| episodesPublishedBefore | No | Only episodes published before this date (YYYY-MM-DD). |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| tip | No | Advisory guidance RAG Web Browser wrote to its key-value store under the reserved "TIP" key | |
| runId | Yes | Actor run ID | |
| stats | No | Run statistics | |
| status | Yes | Run status: READY | RUNNING | TIMING-OUT | TIMED-OUT | ABORTING | ABORTED | SUCCEEDED | FAILED | |
| actorId | Yes | Stable Apify Actor ID from the run record | |
| summary | Yes | Past-tense summary of the run state | |
| exitCode | No | Actor process exit code; populated for terminal states (especially FAILED) | |
| nextStep | Yes | One primary follow-up action with identifiers interpolated | |
| storages | Yes | Dataset and key-value store metadata, keyed by alias. "default" is always the primary entry. | |
| actorName | No | "username/actor-name" | |
| startedAt | No | ISO timestamp when the run started | |
| finishedAt | No | ISO timestamp when the run finished (terminal states only) | |
| statusMessage | No | Pass-through from Apify run.statusMessage | |
| apifyConsoleUrl | No | Personalized Apify Console link to the run; present only for Console sessions |