Audio & Video to Text: Speech to Text Transcription (Whisper)

Transcribe audio and video files and podcast episodes to text with OpenAI's Whisper speech recognition (the fast faster-whisper engine). Paste links to MP3, M4A, WAV, MP4 … or a podcast RSS feed, and get the full transcript with timestamps, ready-made SRT and VTT subtitles and the detected language.

• ✅ 99 languages with automatic language detection, or set the language yourself
• ✅ Translate to English from any language in the same step
• ✅ Podcasts: give the RSS feed and choose how many of the newest episodes to transcribe
• ✅ All common formats: MP3, M4A/AAC, WAV, FLAC, OGG, OPUS, WEBM, MP4, MOV, MKV and more (audio track of videos), up to 2 GB
• ✅ Timestamps: segments with start and end, optional word timestamps with confidence
• ✅ Subtitles: SRT and VTT files with download links
• ✅ Skips silence and music without speech, which also prevents made-up text in quiet parts
• ✅ Vocabulary hint for names, brands and technical terms
• ✅ Cost control: transcribe only the first N minutes of each file; the run stops cleanly at your spending limit
• ✅ Fair billing: per started audio minute; broken links and non-media files are free
• ✅ Private: the audio is transcribed on Apify with the open-source Whisper model; it is not sent to OpenAI or any other outside service

Input example

{
    "mediaUrls": ["https://raw.githubusercontent.com/openai/whisper/main/tests/jfk.flac"],
    "podcastFeedUrls": ["https://feeds.npr.org/510289/podcast.xml"],
    "maxEpisodesPerFeed": 1,
    "model": "base",
    "language": "auto",
    "task": "transcribe",
    "saveSubtitles": true,
    "maxMinutesPerFile": 180
}

Output example

Real output from a test run:

{
    "url": "https://raw.githubusercontent.com/openai/whisper/main/tests/jfk.flac",
    "fileName": "jfk.flac",
    "title": null,
    "podcast": null,
    "published": null,
    "model": "base",
    "task": "transcribe",
    "durationSec": 11,
    "transcribedSec": 11,
    "language": "en",
    "languageProbability": 0.946,
    "billedMinutes": 1,
    "wordCount": 22,
    "text": "And so my fellow Americans ask not what your country can do for you, ask what you can do for your country.",
    "processingSec": 3,
    "segments": [
        { "start": 0, "end": 7.6, "text": "And so my fellow Americans ask not what your country can do for you," },
        { "start": 7.6, "end": 10.6, "text": "ask what you can do for your country." }
    ],
    "srtUrl": "https://api.apify.com/v2/key-value-stores/…/records/000-jfk.srt?signature=…",
    "vttUrl": "https://api.apify.com/v2/key-value-stores/…/records/000-jfk.vtt?signature=…"
}

The SRT file from that run:

1
00:00:00,000 --> 00:00:07,600
And so my fellow Americans ask not what your country can do for you,

2
00:00:07,600 --> 00:00:10,600
ask what you can do for your country.

Podcast episodes also get title, podcast and published. Long transcripts are split into paragraphs at pauses. A summary per file (ok or error with the reason) is saved as OUTPUT in the key-value store.

Speed

Speed depends on the memory you give the run, because Apify assigns CPU in proportion to memory. With the default 4 GB, a 5-minute podcast segment took about 45 seconds with Base and about 2 minutes with Small in our tests; 8 GB is about twice as fast. The price per audio minute stays the same.

Pricing

You pay per started minute of audio that is transcribed. Broken links and non-media files are free.

Apify plan	Base model (default)	Small model
Free	$0.0039 per minute	$0.0100 per minute
Starter	$0.0036	$0.0097
Scale	$0.0034	$0.0094
Business and higher	$0.0031	$0.0091

The Small model is billed as the Audio minute plus the Accurate model minute. Example: a 30-minute podcast costs $0.12 with Base and $0.30 with Small on the Free plan.

FAQ

Which model should I use? base (default) is fast, costs the least and works well for clear speech such as podcasts, talks and meetings. small is more accurate with accents, background noise, several speakers and less common languages, and costs more per minute.

Does it separate speakers? No, the transcript has no speaker labels.

Can I transcribe YouTube, TikTok or Instagram links? No. Use direct links to media files you have the right to use, such as your own recordings, files in cloud storage or podcast feeds.

Is my audio stored? Files are processed inside your run and deleted when it ends. Only the transcript and subtitles are saved in your own storage.

More tools from Tidelane Data

• PDF to Markdown: PDFs to Markdown and text, with tables and OCR for scans
• Image to Text OCR: extract text from images in 26 languages
• RSS Feed Reader: news, blogs and podcasts to JSON
• Website to Markdown: clean Markdown of web pages for AI, LLMs and RAG

All our tools: apify.com/tidelane

---

Impressum

Levi Griesinger, Tidelane Data
Besigheimer Straße 18
74369, Löchgau, Deutschland
E-Mail: LeviGriesinger@gmail.com