Audio to Text Transcription: MP3, WAV & M4A Speech to Text avatar

Audio to Text Transcription: MP3, WAV & M4A Speech to Text

Pricing

from $3.25 / 1,000 minute of transcribed audios

Go to Apify Store
Audio to Text Transcription: MP3, WAV & M4A Speech to Text

Audio to Text Transcription: MP3, WAV & M4A Speech to Text

Transcribe audio files from a link into text: MP3, WAV, M4A, FLAC, OGG and MP4. Get the full transcript with timestamps and optional SRT or VTT subtitles as JSON, CSV or Excel. Whisper AI, 90+ languages, $0.004 per minute, failed files are free.

Pricing

from $3.25 / 1,000 minute of transcribed audios

Rating

0.0

(0)

Developer

Aemon

Aemon

Maintained by Community

Actor stats

0

Bookmarked

2

Total users

1

Monthly active users

4 minutes ago

Last modified

Features

Limited permissions

Share

What does Audio File to Text do?

Audio File to Text turns audio files into text. Paste links to MP3, WAV, M4A, FLAC, OGG or MP4 files and get the full transcript, timestamped segments, the detected language and optional SRT or VTT subtitles, one row per file, as JSON, CSV or Excel. It uses Whisper large-v3-turbo, works in 90+ languages and needs no account anywhere except Apify.

  • 💸 $0.004 per minute of audio, about $0.24 per hour, platform usage included. Files that fail are free.
  • 🎧 Any common format: MP3, M4A, AAC, WAV, FLAC, OGG, OPUS, MP4, MOV and WEBM from any public link (cloud storage, a CDN, your own server, a podcast host).
  • 🌍 90+ languages, detected automatically, or pick the language yourself.
  • ⏱️ Long recordings are fine: interviews, lectures and meetings of 2–3 hours are split and transcribed automatically.
  • 📝 Ready for AI: clean text plus segments with start and end times, ready for ChatGPT, Claude, RAG pipelines, search and subtitles.
  • 🔗 Built for automation: one HTTP request from n8n, Make or Zapier, or a tool for AI agents through the Apify MCP server.

What you get

One row per file (real output for the prefilled example, empty fields left out):

{
"status": "ok",
"episodeTitle": "jfk.flac",
"audioUrl": "https://github.com/openai/whisper/raw/main/tests/jfk.flac",
"durationSec": 11,
"language": "en",
"hasSpeech": true,
"text": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
"wordCount": 22,
"segments": [
{ "start": 0, "end": 10.4, "text": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country." }
],
"srt": "1\n00:00:00,000 --> 00:00:10,400\nAnd so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.\n",
"inputUrl": "https://github.com/openai/whisper/raw/main/tests/jfk.flac"
}
FieldWhat it is
textThe whole transcript as one clean text
segmentsParts of the transcript with start and end in seconds
srt / vttSubtitle file, when you pick a subtitle format
languageDetected (or chosen) language code
durationSec, wordCountLength of the audio and number of words
hasSpeechfalse when the file is only music or silence
episodeTitle, audioUrl, inputUrlFile name and the link it came from

The default view is a table with the transcripts; export it as JSON, CSV, Excel or HTML, or read it through the API.

What can you use audio transcription for?

  • Interviews and research: turn recorded interviews into text you can search, quote and code.
  • Meetings, lectures and webinars: notes and searchable archives from recordings.
  • Voice notes and call recordings: get the text into your CRM, Notion or a spreadsheet.
  • Subtitles: SRT or VTT files for videos and courses.
  • AI pipelines: feed transcripts into ChatGPT, Claude, LangChain or a vector database for summaries, Q&A and RAG.

How to convert an audio file to text

  1. Click Try for free (the Apify free plan's $5 monthly credit transcribes about 20 hours of audio).
  2. Paste one or more links into Audio file URLs. Each link must download the file directly.
  3. Optionally pick the spoken language, timestamps and a subtitle format.
  4. Click Start and download the transcripts.

Ready-to-run examples

Each example opens a pre-filled setup that you can run in one click and save as your own task:

Pricing

You pay $0.004 per started minute of transcribed audio. Platform usage (compute and downloads) is included.

AudioPrice
1-minute voice note$0.004
30-minute interview$0.12
1-hour lecture$0.24
100 hours of recordings$24
  • Files that cannot be downloaded or transcribed are free and reported with an error code.
  • Use Skip files longer than and the run's maximum cost setting to stay in budget. The Actor never charges more than the limit you set.
  • Apify Starter, Scale and Business plans get lower per-minute prices automatically.

Input example

{
"urls": [
"https://github.com/openai/whisper/raw/main/tests/jfk.flac",
"https://example.com/recordings/interview.mp3"
],
"language": "auto",
"includeSegments": true,
"subtitleFormat": "srt"
}

Use it from code, AI agents and automations

Input example

{
"urls": [
"https://github.com/openai/whisper/raw/main/tests/jfk.flac"
],
"includeSegments": true,
"subtitleFormat": "srt"
}

JavaScript

import { ApifyClient } from 'apify-client';
const client = new ApifyClient({ token: 'YOUR_APIFY_TOKEN' });
const run = await client.actor('aemon/audio-file-to-text').call({"urls":["https://github.com/openai/whisper/raw/main/tests/jfk.flac"],"includeSegments":true,"subtitleFormat":"srt"});
const { items } = await client.dataset(run.defaultDatasetId).listItems();
console.log(items);

Python

from apify_client import ApifyClient
client = ApifyClient("YOUR_APIFY_TOKEN")
run = client.actor("aemon/audio-file-to-text").call(run_input={"urls":["https://github.com/openai/whisper/raw/main/tests/jfk.flac"],"includeSegments":True,"subtitleFormat":"srt"})
for item in client.dataset(run["defaultDatasetId"]).iterate_items():
print(item)

AI agents (MCP): Claude, ChatGPT, Cursor

This Actor works as a tool in any MCP client through the Apify MCP server. Add it to the MCP configuration of Claude Desktop, Claude Code, Cursor or VS Code, with your Apify API token:

{
"mcpServers": {
"apify": {
"url": "https://mcp.apify.com?tools=aemon/audio-file-to-text",
"headers": { "Authorization": "Bearer YOUR_APIFY_TOKEN" }
}
}
}

Then ask your agent in plain words, for example: "Transcribe this MP3 into text with timestamps and give me the three main points: https://example.com/interview.mp3"

Agents without an Apify account can still use it: the Actor accepts agentic payments, so an agent can run it and pay per run with x402 (USDC) or a Skyfire token instead of an API token.

n8n, Make and Zapier

One HTTP request runs the Actor and returns the results, so it fits into any automation tool:

POST https://api.apify.com/v2/acts/aemon~audio-file-to-text/run-sync-get-dataset-items?timeout=300
Authorization: Bearer YOUR_APIFY_TOKEN
Content-Type: application/json
{"urls":["https://github.com/openai/whisper/raw/main/tests/jfk.flac"],"includeSegments":true,"subtitleFormat":"srt"}

In n8n use an HTTP Request node, in Make HTTP → Make a request and in Zapier Webhooks by Zapier → Custom Request. Every file comes back as one item, ready for Google Sheets, Notion, Slack or email. You can also connect integrations and webhooks directly in the Integrations tab.

Ask an AI assistant about this Actor

Open a ready-made question about this Actor in ChatGPT, Claude or Perplexity.

Errors are free and explained

Every link you paste gets a row. If a file cannot be processed, the row has "status": "error", an errorCode and a readable error message, and it is not charged:

Error codeWhat it means
UNAVAILABLEThe link returned "not found" (HTTP 404 or 410).
DOWNLOAD_FAILED / NETWORKThe file could not be downloaded, for example because it needs a login. Temporary problems are retried automatically first.
TOO_LARGEThe file is bigger than 1.5 GB.
TOO_LONGThe audio is longer than Skip files longer than.
UNSUPPORTED_URLThe text is not a valid link.

FAQ

Where do my files need to be? At a public link that downloads the file directly, such as cloud storage with a public link, a CDN, your own server or a podcast host. Files that need a login cannot be downloaded.

How long can a file be? Up to 10 hours and 1.5 GB. Long recordings are split and transcribed in parts automatically.

Which formats work? MP3, M4A, AAC, WAV, FLAC, OGG, OPUS, and the audio track of MP4, MOV, MKV and WEBM videos.

How accurate is it? It uses Whisper large-v3-turbo, one of the most accurate open speech recognition models. It handles accents, background noise and technical vocabulary well.

Does it identify speakers? Not yet: the transcript has timestamps but no speaker labels. Tell us in the Issues tab if you need speaker detection.

Are my files stored? No. Each file is downloaded for the run, transcribed and deleted. Only the transcript is saved, in your own dataset.

Can it transcribe podcasts or videos from websites? Yes: for Apple Podcasts, Spotify, RSS feeds and AI summaries use Podcast to Text, and for Instagram, TikTok, X and Facebook videos use Video to Text.

More Actors by Aemon

  • Podcast to Text: Apple Podcasts, Spotify and RSS episodes to text with AI summaries, same $0.004 per minute
  • YouTube Transcript Scraper: transcripts of YouTube videos, channels and searches, $0.002 per video
  • Video to Text: Instagram, TikTok, X and Facebook transcripts with Whisper AI

Support

Found a file that does not work or need a feature? Open an issue in the Issues tab; issues are answered within a day. If the Actor saves you time, a rating on the Reviews tab helps others find it.

Built and maintained by Aemon.