🎙️ Audio & Video Transcription Actor

Transform hours of audio and video into accurate, searchable text in minutes.

---

⚡ Why Choose This Actor?

Feature	Benefit
🚀 Lightning Fast	Process hours of audio 10x faster than real-time
🌍 99+ Languages	Auto-detect or specify any of 99 supported languages
📁 Any Source	Google Drive, Dropbox, S3, Supabase, and 15+ cloud services
🎬 Audio & Video	MP3, WAV, MP4, WebM, M4A, and more
⏱️ Timestamps	Word-level and segment timestamps for subtitles
💾 Memory Efficient	Handle files up to 500MB without crashes

---

🎯 Perfect For

• 🎧 Podcasters — Turn episodes into blog posts and show notes
• 📹 Content Creators — Generate subtitles and captions automatically
• 🏢 Businesses — Transcribe meetings, calls, and webinars
• 🔬 Researchers — Build datasets from interviews and focus groups
• 📚 Educators — Create searchable lecture archives

---

📊 Supported Formats

Audio Formats

Format	Extension	Support
MP3	.mp3	✅ Full
WAV	.wav	✅ Full
M4A/AAC	.m4a	✅ Full
OGG Vorbis	.ogg	✅ Full
FLAC	.flac	✅ Full
MPEG Audio	.mpeg, .mpga	✅ Full

Video Formats (Audio Extraction)

Format	Extension	Support
MP4	.mp4	✅ Full
WebM	.webm	✅ Full

---

☁️ Supported Cloud Sources

Paste a link from any of these services — we handle the conversion automatically:

📦 Cloud Storage

Service	Direct Link Support	Auto-Convert
Google Drive	✅	✅ Converts /view to download
Dropbox	✅	✅ Converts ?dl=0 to ?dl=1
OneDrive	✅	✅ Auto-converts sharing links
Box	✅	✅ Converts to static link
iCloud	⚠️ Requires direct link	—

🔧 Developer Platforms

Service	Direct Link Support	Notes
AWS S3	✅	Public buckets
Google Cloud Storage	✅	Public objects
Azure Blob Storage	✅	Public containers
Backblaze B2	✅	Public files
Supabase Storage	✅	Public buckets
Firebase Storage	✅	Auto-adds ?alt=media
Cloudinary	✅	Direct URLs

🌐 Other Sources

Service	Support	Notes
GitHub	✅	Auto-converts blob to raw
Airtable	✅	Attachment URLs
Notion	✅	Follows S3 redirects
Any Direct URL	✅	HTTP/HTTPS links

---

🌍 99+ Supported Languages

Auto-detect any language or specify explicitly for better accuracy:

---

🚀 Quick Start

Run in Apify Console

1. Paste your audio/video URL
2. Select source language (or leave as "Auto-detect")
3. Click Start and get your transcript!

---

📥 Input Parameters

Parameter	Type	Required	Default	Description
audioUrl	string	✅ Yes	—	URL to audio/video file (supports cloud storage links)
sourceLanguage	string	No	auto	Source language code or auto for detection

---

📤 Output Format

{
  "plain_text": "Full transcription as clean, readable text...",
  "detected_language": "en",
  "duration_seconds": 3600,
  "audio_url": "https://example.com/audio.mp3",
  "verbose": {
    "language": "en",
    "duration_seconds": 3600,
    "segments": [
      {
        "id": 0,
        "start": 0.0,
        "end": 4.52,
        "text": "Welcome to today's episode."
      }
    ],
    "words": [
      { "start": 0.0, "end": 0.48, "word": "Welcome" },
      { "start": 0.48, "end": 0.72, "word": "to" },
      { "start": 0.72, "end": 1.12, "word": "today's" },
      { "start": 1.12, "end": 1.56, "word": "episode" }
    ]
  }
}

Export Options

• JSON — Full structured data with timestamps
• CSV — Tabular format for spreadsheets
• Excel — Direct download for analysis
• Plain Text — Clean transcript without metadata

---

💰 Pricing

Simple, transparent pay-per-use pricing:

Audio Duration	Cost
1 minute	$0.10
10 minutes	$1.08
1 hour	$6.48

Rate: $0.0018 per second of audio processed

💡 Tip: Only pay for actual audio duration, not processing time!

---

⚙️ Technical Specifications

Performance

• ⚡ Processing Speed: Up to 10x faster than real-time
• 📊 Accuracy: 95%+ for clear audio in supported languages

---

🔧 Troubleshooting

Issue	Solution
"URL returned HTML"	Ensure file is publicly shared (Google Drive: "Anyone with link")
Wrong language detected	Set sourceLanguage explicitly instead of auto
Processing timeout	Increase Actor memory in run settings

---

📋 Use Cases & Examples

🎧 Podcast Transcription

{
  "audioUrl": "https://podcast-cdn.com/episode-142.mp3",
  "sourceLanguage": "auto"
}

📹 Video Subtitle Generation

{
  "audioUrl": "https://storage.googleapis.com/bucket/video.mp4",
  "sourceLanguage": "en"
}

🎤 Meeting Recording

{
  "audioUrl": "https://drive.google.com/file/d/XXX/view",
  "sourceLanguage": "auto"
}

---

🔒 Privacy & Compliance

• Audio files are processed and immediately deleted
• No data retention beyond the Actor run
• GDPR-compliant processing
• You control your data exports

⚠️ Important: Only process audio you have rights to use.

---

🤝 Support & Feedback

• 🐛 Bug Reports: Use the Issues tab on the Actor page
• 💡 Feature Requests: Open an Issue with your use case
• 📧 Custom Integrations: Contact via Apify

---