Audio Transcription: Speech to Text, MP3 & Podcast to Text, SRT avatar

Audio Transcription: Speech to Text, MP3 & Podcast to Text, SRT

Pricing

from $3.00 / 1,000 audio minutes

Go to Apify Store
Audio Transcription: Speech to Text, MP3 & Podcast to Text, SRT

Audio Transcription: Speech to Text, MP3 & Podcast to Text, SRT

Transcribe audio and video files and podcast episodes to text with Whisper: 99 languages, timestamps, SRT/VTT subtitles, translation to English. $3 per 1,000 audio minutes.

Pricing

from $3.00 / 1,000 audio minutes

Rating

0.0

(0)

Developer

Giorgos Myrianthous

Giorgos Myrianthous

Maintained by Community

Actor stats

0

Bookmarked

3

Total users

2

Monthly active users

13 days ago

Last modified

Features

Limited permissions

Share

Speech to text with Whisper for audio and video files and podcast RSS feeds: MP3, M4A, WAV, OGG, FLAC, MP4, MOV and WEBM to text, timestamped segments and SRT/VTT subtitles, in 99 languages, with optional translation to English. Half the price of most Whisper transcribers on the Store.

💲 $0.003 per audio minute ($3 per 1,000 minutes) with the tiny/base model, $0.006 with the more accurate small model. Failed files are free. Pay only for results. No subscription, and the Apify free plan's monthly credit covers small jobs.

Also known as: audio transcription, speech to text, Whisper transcription, MP3 to text, podcast transcript, audio to text, video to text, SRT subtitles generator, transcribe audio API.

Try it now (free-plan friendly)

  1. Click Start. The prefilled input works as is. Transcribes JFK's famous 11-second quote in about 10 seconds.
  2. Or paste this input into the JSON tab:
{
"audioUrls": [
{
"url": "https://raw.githubusercontent.com/ggml-org/whisper.cpp/master/samples/jfk.wav"
}
]
}

Example output (one dataset item, shortened):

{
"url": "https://raw.githubusercontent.com/ggml-org/whisper.cpp/master/samples/jfk.wav",
"status": "ok",
"language": "en",
"durationSec": 11.0,
"minutesCharged": 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.",
"srtUrl": "https://api.apify.com/v2/key-value-stores/…/records/jfk.wav-1.srt",
"segments": [
{
"start": 0.0,
"end": 7.6,
"text": "And so my fellow Americans ask not what your country can do for you,"
}
]
}

Small runs cost cents, and you can set a Max cost per run so you're never charged more.

Use with AI agents / Apify MCP

Give your agent (Claude, ChatGPT, Cursor, n8n AI Agent, LangChain, OpenAI Agents SDK) this tool through Apify's MCP server:

https://mcp.apify.com?tools=gmyri/audio-transcriber
  • Example prompt: "Transcribe the latest episode of this podcast feed and summarise it: https://feeds.npr.org/510289/podcast.xml"
  • Why agents like it: the input has one required field and documented defaults and enums. The output has stable, flat field names, errors are returned as items with an error field and are never charged, and each run writes a summary to the OUTPUT record.
  • Agents that use search-actors find it by searching for: audio transcription, speech to text.

API, Python, n8n, Make, Zapier

curl -X POST "https://api.apify.com/v2/acts/gmyri~audio-transcriber/run-sync-get-dataset-items?token=$APIFY_TOKEN" \
-H 'Content-Type: application/json' \
-d '{"podcastFeeds":["https://feeds.npr.org/510289/podcast.xml"],"episodesPerFeed":1,"model":"base"}'
  • Python: ApifyClient(token).actor("gmyri/audio-transcriber").call(run_input={...})
  • n8n / Make / Zapier: use the Apify "Run Actor" action with gmyri/audio-transcriber, then read the dataset items.

Quick FAQ

  • Does it work with YouTube or Spotify links? No. Platform pages aren't supported. Use a direct audio/video file URL you have the right to process, or a public podcast RSS feed.
  • How fast is it? With 4 GB memory (1 vCPU) the base model transcribes about 14 minutes of audio per minute; the default 2 GB is half that speed at the same cost per minute. Use more memory for more speed, or tiny.
  • Which languages? All 99 Whisper languages, auto-detected. Set language to force one, or translateToEnglish for English output.
  • What if I set a spending limit? The Actor stops cleanly at your Max cost per run and you're never charged above it.

Details

What it does

  • Speech to text with OpenAI Whisper (faster-whisper, int8) running on Apify. No OpenAI key, no per-request API bill on top.
  • Any audio or video file URL: MP3, M4A, WAV, OGG, OPUS, FLAC, AAC, MP4, MOV, WEBM. Signed S3/GCS/Dropbox links work.
  • Podcast to text: give a podcast RSS feed and it transcribes the newest episodes from the feed's enclosures.
  • 99 languages, auto-detected, plus translation to English.
  • Timestamps and subtitles: segments with start/end times, optional word-level timestamps, and SRT / VTT / TXT files saved for every file.
  • Voice activity detection skips silence and reduces Whisper hallucinations.

Typical uses

  • Podcast, interview and meeting-recording transcripts for search, SEO, show notes and RAG.
  • Subtitles (SRT/VTT) for your own videos.
  • Feeding call recordings or voice notes you own into LLM pipelines and AI agents.
  • Scheduled podcast monitoring: combine with an Apify schedule and episodesPerFeed: 1.

Input

FieldDescription
audioUrlsDirect audio/video file URLs.
podcastFeedsPodcast RSS feeds (newest episodes are transcribed).
episodesPerFeedEpisodes per feed (default 1).
modeltiny, base (default) or small (more accurate, billed at the small rate).
languageISO code (en, de, es, el...) or empty to auto-detect.
translateToEnglishOutput an English translation.
includeSegments, wordTimestamps, saveSubtitlesTimestamp and subtitle options.
maxMinutesPerFileSkip files longer than this (default 180).

Pricing

Pay per event: $0.003 per audio minute ($3 per 1,000 minutes) with the tiny or base model, $0.006 per minute with the small model, plus Apify's standard $0.00005 Actor start. Minutes are rounded up per file (an 11-second clip is 1 minute). Failed downloads, unsupported links and skipped files are free.

Notes

  • Only process audio you own or have the right to transcribe. Video/social platform pages (YouTube, TikTok, Instagram, Spotify...) are not supported: pass a direct file URL or a public podcast feed.
  • Transcripts may contain whatever was said in the audio. The Actor stores results only in your own Apify storage.
  • CPU Whisper is fast: a 35-minute episode takes well under a minute with tiny and a few minutes with base.

💡 Need several checks per site? Website Audit All-in-One runs SEO, broken links, PageSpeed, tech stack and SSL/DNS checks in one report for $0.03 per site.

All tools by gmyri: doc-to-markdown, dataset-merge-dedup, site-health-audit, website-screenshot, domain-health-check, image-pdf-ocr, tech-stack-detector, rss-feed-reader, pagespeed-checker, website-audit, wayback-machine-snapshots, image-converter.