Podcast & Audio Transcription with Speaker Labels (SRT, VTT)

Transcribe podcasts, interviews, meetings and videos with speaker labels and timestamps, and get ready-to-use SRT and VTT subtitles. Give it audio or video links, or a podcast's RSS feed, and it returns who said what, when, for every recording. On a schedule with Only new episodes, it transcribes each new episode of a show and nothing twice.

Speaker labels, word-level timing and both subtitle formats are included in one per-minute price, not sold as extras.

What you get

For each recording:

• the transcript as text, one paragraph per speaker turn (Speaker 1: ..., Speaker 2: ...);
• segments with start and end times in seconds, the text and the speaker, ready for search, quotes, chapters or AI pipelines;
• SRT and VTT subtitle files in the run's key-value store (speaker names included);
• the episode's title, link and publication date when it came from a feed.

Input

Field	What it does
Audio or video links	Direct links to MP3, M4A, WAV, MP4, WEBM, OGG or FLAC files, up to 1 GB each.
Podcast RSS feeds	The newest episodes of each feed are transcribed.
Episodes per feed	How many of the newest episodes (default 3).
Only new episodes	Transcribe, and pay for, only episodes published since your last run. The first run transcribes the newest ones and remembers the older episodes in the feed as already there. Perfect for a daily or weekly schedule.
State name	Separate memory per schedule.
Language	Two-letter code (en, de, es, fr, ...), or empty to detect it.
Speaker labels	On by default.
Maximum minutes per recording	Longer recordings are transcribed up to this length (default 240).

{
  "feeds": ["https://feeds.example.com/podcast.xml"],
  "maxEpisodesPerFeed": 5,
  "onlyNew": true,
  "language": "en"
}

Output

One dataset item per recording:

{
  "url": "https://cdn.example.com/episodes/42.mp3",
  "episodeTitle": "Episode 42: Searching twenty years of contracts",
  "publishedAt": "2026-10-14T08:00:00.000Z",
  "status": "ok",
  "durationSeconds": 2735,
  "language": "eng",
  "speakers": 2,
  "text": "Speaker 1: Welcome back to the show. ...\n\nSpeaker 2: Thanks for having me. ...",
  "segments": [
    { "start": 0.6, "end": 6.9, "text": "Welcome back to the show.", "speaker": "Speaker 1" }
  ],
  "files": {
    "txt": "https://api.apify.com/v2/key-value-stores/<store-id>/records/001-transcript.txt",
    "srt": "https://api.apify.com/v2/key-value-stores/<store-id>/records/001-transcript.srt",
    "vtt": "https://api.apify.com/v2/key-value-stores/<store-id>/records/001-transcript.vtt"
  },
  "error": null
}

Pricing

Pay per event: one audio minute for each started minute transcribed, plus Apify's small start fee per run. Speaker labels, timestamps, SRT and VTT are included. Recordings that fail (broken links, files that aren't audio) are not charged.

Apify's free plan transcribes up to 10 minutes per run (longer recordings: the first 10 minutes), enough to try it; paid Apify plans have no such limit. The Maximum cost per run you set is respected: a recording that would go past it is transcribed up to the limit and marked trimmed, and the rest are skipped. With Only new episodes, an episode cut short by the cost limit is transcribed again in full on the next run.

Good to know

• Recordings longer than 2 hours 20 minutes are transcribed in parts of that length; speaker numbering can restart in each part.
• With Only new episodes, set Episodes per feed to at least the number of episodes published between your runs; any left over are picked up by the next run.
• A recording without speech (silence, music only) returns an empty transcript with a note and is charged by its length, like any processed audio.
• Transcription quality depends on the audio: clear speech gives the best results; heavy music, crosstalk and strong noise give weaker text and speaker labels.
• Only transcribe recordings you have the right to use. The audio is sent to a third-party speech-to-text service (ElevenLabs Scribe v2, reached through OpenRouter) to be transcribed; we keep no copy of your files or transcripts, and the results stay in your own Apify storage. Check that this is acceptable for confidential recordings.

FAQ

Which languages? Dozens, detected automatically; setting the language helps for short clips.

Can I use it in Make, Zapier or n8n? Yes, through Apify's integrations or the Apify API.

Support: support+transcription@iiclabs.com. Include the run ID if something looks wrong. If it saved you time, a rating on this page helps others find it.