Wisprs — AI Transcription & Subtitle Generator (YouTube, Podcast, Audio)

Submit any YouTube video, podcast episode, or audio URL and get back a full text transcript, SRT/VTT subtitles, speaker-labeled segments, and structured content like show notes, chapters, or Twitter/X threads — saved to your Apify Dataset automatically.

The Wisprs Transcription Actor is powered by the Wisprs API, a production-grade async voice processing engine that transcribes audio from any publicly accessible URL. Unlike caption-scraping actors that fail on 30–40% of videos (music, Shorts, unlisted), Wisprs uses Whisper-based transcription and yt-dlp to cover 100% of video and audio URLs. Accuracy is excellent on clear audio; results vary by language, accent, and recording quality.

---

What does this Actor do?

1. Takes a list of YouTube, podcast, or audio/video URLs from your startUrls input
2. Submits each URL to the Wisprs transcription API (async job queue — no timeouts)
3. Polls until each job completes (typically 1–3 minutes per 15-minute video)
4. Exports the transcript in your chosen formats: TXT, SRT, VTT, JSON, or Markdown
5. Optionally generates structured content from the transcript via the Wisprs repurpose engine — podcast show notes, timestamped chapters, guest quotes, Twitter/X threads, or blog posts
6. Saves one dataset row per URL — ready for downstream automation

---

How do I transcribe a YouTube video to SRT subtitles?

Set exportFormats to include "srt" and run:

{
  "startUrls": [{ "url": "https://www.youtube.com/watch?v=YOUR_VIDEO_ID" }],
  "language": "auto",
  "exportFormats": ["srt", "txt"],
  "repurposeMode": "none"
}

Each dataset row will contain the full SRT file in transcript_srt and plain text in transcript_txt. Works for captionless videos, unlisted videos, and anything with audio.

---

How do I transcribe a podcast episode with speaker labels?

Enable diarize: true to get speaker-attributed segments:

{
  "startUrls": [{ "url": "https://your-podcast-host.com/episode.mp3" }],
  "language": "auto",
  "diarize": true,
  "exportFormats": ["txt", "srt", "vtt"]
}

Speakers are labeled "Host", "Guest", "Speaker 1", "Speaker 2", etc. Works best on clear two-speaker recordings; handles up to 6–8 speakers on clean audio.

---

How do I generate show notes, chapters, or a Twitter thread from a video?

Set repurposeMode to your desired output and the Actor transcribes first, then generates content from the real transcript:

{
  "startUrls": [{ "url": "https://www.youtube.com/watch?v=YOUR_VIDEO_ID" }],
  "exportFormats": ["txt", "srt"],
  "repurposeMode": "show-notes"
}

Available modes: summary, show-notes, thread, chapters, quotes, blog.

---

How do I batch transcribe an entire podcast back-catalog?

Add all episode URLs to startUrls. The Actor processes them sequentially, saving each result to the Dataset as it completes — no timeout, no manual polling required:

{
  "startUrls": [
    { "url": "https://anchor.fm/.../episode-1.mp3" },
    { "url": "https://anchor.fm/.../episode-2.mp3" },
    { "url": "https://anchor.fm/.../episode-3.mp3" }
  ],
  "exportFormats": ["txt", "md"],
  "diarize": true
}

---

How do I use this with n8n, Make, or Zapier?

Pass a webhookUrl in your input. The Wisprs API will POST the completed job result to your endpoint as each transcription finishes — no need to poll from your workflow:

{
  "startUrls": [{ "url": "https://www.youtube.com/watch?v=YOUR_VIDEO_ID" }],
  "exportFormats": ["txt", "srt"],
  "webhookUrl": "https://your-n8n-instance.com/webhook/YOUR_HOOK_ID"
}

The webhook payload includes transcriptionId, status, durationSeconds, language, and the full transcript text.

---

Using with AI agents (MCP)

This Actor is published on the Apify Store and automatically available as an MCP tool. AI agents using Claude Desktop, LangChain, CrewAI, or any MCP-compatible framework can discover and call this Actor with a single Apify MCP configuration — no custom integration required.

---

What data does the Actor return?

Each dataset row includes:

Field	Description
url	The submitted URL
jobId	Wisprs transcription ID (integer)
transcriptionId	Same as jobId — the transcription ID
status	completed or failed
durationSeconds	Audio/video duration in seconds
language	ISO 639-1 code of the detected language (e.g. "en", "es")
transcript_txt	Full plain-text transcript
transcript_srt	SRT subtitle file content
transcript_vtt	WebVTT subtitle file content
transcript_json	Word-level timestamps in JSON
transcript_md	Transcript in Markdown format
repurposed_show-notes	Structured show notes (summary, chapters, quotes)
repurposed_thread	Twitter/X thread text
repurposed_blog	Markdown blog post or LinkedIn article
repurposed_summary	2–4 sentence summary
repurposed_chapters	Timestamped chapter markers
repurposed_quotes	Top verbatim quotes

---

Wisprs vs caption-scraping transcription actors

Feature	Wisprs	Caption scrapers
Works on captionless videos	Yes	No
Works on YouTube Shorts	Yes	Partial
Works on private-link Loom / mp3 / mp4	Yes	No
SRT / VTT subtitle export	Yes	Text only (usually)
Speaker diarization	Yes	No
Repurpose to thread / blog / chapters	Yes	No
Webhook per completed job	Yes	No
100+ languages	Yes	~20–30 typically

---

How much does it cost?

Pricing is pay-per-event:

• $0.005 per transcription submitted (one-time per URL)
• $0.015 per audio minute processed (e.g. a 30-minute episode = $0.45)
• $0.075 per repurpose result generated (show notes, thread, etc.)

Example: 10 podcast episodes averaging 45 minutes each

• Submission: 10 × $0.005 = $0.05
• Audio minutes: 10 × 45 × $0.015 = $6.75
• Show notes (optional): 10 × $0.075 = $0.75
• Total: ~$7.55 for 10 complete episodes with show notes

The Apify free plan includes $5 of monthly credits — enough to transcribe 5–6 short videos at no cost.

---

Input

Field	Type	Required	Default	Description
startUrls	Array	Yes	—	YouTube, podcast, or audio/video URLs
apiKey	String	No	—	Your Wisprs API key (optional — publisher key used by default)
language	String	No	auto	ISO 639-1 code or auto
diarize	Boolean	No	false	Label speakers (host vs guest)
exportFormats	Array	No	["txt","srt"]	txt, srt, vtt, json, md
repurposeMode	String	No	none	none, summary, show-notes, thread, chapters, quotes, blog
webhookUrl	String	No	—	Callback URL per completed job
maxPollSeconds	Integer	No	900	Max wait per job (60–3600s)
pollIntervalSeconds	Integer	No	10	Status check interval (5–60s)

---

Supported URLs

• YouTube videos, Shorts, and playlist-linked videos
• Direct audio: mp3, wav, m4a, ogg, flac
• Direct video: mp4, webm, mov
• Podcast RSS episode links
• TikTok, Loom, Vimeo, and most public video/audio hosts

---

Language support

100+ languages with automatic detection. The detected language appears in each dataset row as language. Pass a specific ISO 639-1 code ("en", "es", "fr") to skip auto-detection and speed up processing slightly for known-language content.

---

Related Actors

• Wisprs — Podcast Show Notes Generator — podcast episodes → show notes, chapters, guest quotes with speaker diarization
• Wisprs — YouTube Content Repurposer — YouTube → Twitter thread, LinkedIn article, blog post, chapters
• Wisprs — Social Media Transcriber — TikTok, Instagram Reels, YouTube Shorts at $1.00/1k

---

FAQ

Do I need an OpenAI API key or a Wisprs account? No. No external API key or account required. The Actor handles authentication internally — you pay only via Apify credits.

Does it work for videos without captions? Yes. Unlike caption-scraping actors, Wisprs transcribes the audio directly using Whisper. It covers captionless videos, music videos, private-link Loom recordings, and anything with audio.

Is there a video length limit? No hard limit. The async job queue handles videos of any length. A 90-minute webinar typically completes in 5–10 minutes.

What if a job fails? The dataset row will have status: "failed". Check the Actor logs for details (unsupported format, private video, no audio, etc.).

---

Support

• Documentation: wisprs.co/docs
• Email: tosh@belvadigital.com
• Issues: report via the Apify Actor page

---

Submit a URL. Get subtitles, transcripts, and show notes. Done.