Transcribe the newest NPR News Now episode, 1 episode

What this example returns

This example returns up to 1 episode.

The dataset’s “Transcripts” view shows 13 columns: Title, Podcast, Language, Translated to, Duration (s), Billed min, Words, Transcript, SRT, TXT, Status, Input URL, and Warning. See every output field.

What each setting does

The input this example runs Audio & Video Transcriber with. “Try this input” opens it in the console, where you can run it as-is or change any field first.

Media files, podcast feeds or pages urls

https://podcasts.apple.com/us/podcast/npr-news-now/id121493675

One per line. YouTube video links, TikTok video links (tiktok.com/@user/video/... or vm.tiktok.com share links), direct audio or video file links (MP3, M4A, WAV, OGG, OPUS, FLAC, AAC, MP4, MOV, WEBM...), podcast RSS feeds, Apple Podcasts show or episode links, or web pages that embed an audio or video file. Google…

Episodes per podcast feed maxEpisodesPerFeed

1

How many of the newest episodes to transcribe from each podcast feed or Apple Podcasts show.

Speech model model

Tiny (fastest)

Speed vs. accuracy. 'base' is a good default for clear speech. 'small' is the most accurate (noisy audio, accents, non-English) but about 3x slower, so it uses more compute. 'tiny' is the fastest.

Default: Base (balanced) → this example uses Tiny (fastest)

Translate to English translateToEnglish

No

Output an English translation of the speech instead of a transcript in the original language (built into the speech model, no extra charge). For other languages, use 'Translate to'.

Word timestamps wordTimestamps

No

Add start and end times for every word inside each segment (slightly slower).

Skip silence and music skipSilence

Yes

Detect speech first and skip long silences and pure music. Faster, and it prevents made-up text in silent parts.

Beam size beamSize

1

1 is fastest. Higher values (up to 5) can be a little more accurate but take longer.

Max minutes per file maxMinutesPerFile

5

Longer files are transcribed up to this many minutes and billed only for what was transcribed. Maximum 300.

Default: 120 → this example uses 5

Timestamped segments includeSegments

Yes

Add the list of segments with start and end times to each row.

Save SRT, VTT and TXT files saveSubtitleFiles

Yes

Save subtitle files (SRT, VTT) and a plain-text transcript for every file in the run's key-value store and link them in the row (srtUrl, vttUrl, txtUrl).

SRT and VTT text in the row subtitlesInDataset

No

Also put the full SRT and VTT subtitle text into each row.

Max file size (MB) maxFileSizeMb

1024

Skip media files larger than this. Video files are much bigger than audio for the same length.

{
  "urls": [
    "https://podcasts.apple.com/us/podcast/npr-news-now/id121493675"
  ],
  "model": "tiny",
  "maxEpisodesPerFeed": 1,
  "translateToEnglish": false,
  "wordTimestamps": false,
  "skipSilence": true,
  "beamSize": 1,
  "maxMinutesPerFile": 5,
  "includeSegments": true,
  "saveSubtitleFiles": true,
  "subtitlesInDataset": false,
  "maxFileSizeMb": 1024
}

What it costs

You pay for the events the actor reports, such as each result or page it produces. Platform usage is included in the event prices: compute, proxies, browser and storage cost nothing extra.

• Audio minute transcribedfrom $0.0144Charged per started minute of audio actually transcribed in each file. Failed downloads, invalid URLs and files with no speech are free.
• Actor startfrom $0.003Charged once per run.
• Translated audio minute$0.0017Only with 'Translate to': charged per transcribed minute whose transcript was translated into the chosen language. Not charged when the translation fails.

Full pricing

Other ways to run Audio & Video Transcriber

• Transcribe a historic 1921 speech, 2 minutesTimed text segments and subtitles from an audio file.

All examples of Audio & Video Transcriber

About Audio & Video Transcriber

Transcribe YouTube and TikTok videos, audio and video files, podcast RSS feeds and Apple Podcasts episodes to text with timestamps, language detection, SRT/VTT subtitles and translation into any language. Pay per audio minute. No login needed.

Price:

From $14.40 / 1,000 audio minutes transcribed

Developer:

Toolwright

Categories:

AI, Videos, Automation

Audio & Video Transcriber pageOutput fieldsPricing