Audio Transcriber - Speech to Text

Audio Transcriber - Speech to Text

Transcribe any audio file to text, from a URL or direct upload, in minutes. Get back a clean transcript with timestamps, detected language, and confidence scores. No API key, no setup. Export to JSON, CSV, Excel, or XML.

Most speech-to-text tools lock you into a single provider, charge per minute, or force you to build a pipeline to test one file. This Actor takes a public audio URL or a direct upload, runs it through a production transcription model, and returns the full text in one flat record. It handles WAV, MP3, AIFF, AAC, OGG, FLAC, and other common formats, and you can steer accuracy with an ISO language code.

Who uses it	What they scrape Audio Transcriber for
Podcast producers	Turn raw episode audio into a searchable transcript for show notes and SEO
Market researchers	Convert recorded interviews or focus groups into text for qualitative analysis
Content marketers	Repurpose webinar or video audio into blog posts and social snippets
Accessibility teams	Generate captions or transcripts for audio content to meet compliance needs
Data analysts	Feed call center or meeting recordings into text mining pipelines

What it does

This Actor collects the spoken content of an audio file and returns it as a single transcript record with timestamps, language, and confidence metadata.

• 🎧 Direct upload or URL: pass a public audio file URL or upload the file directly in the Apify UI, no hosting required.
• 🌍 Language steering: set an ISO 639-1 code like 'en', 'es', or 'pt' to improve recognition of accents and domain terms.
• ⏱️ Timestamped segments: each transcript row includes start and end times so you can jump to the exact moment.
• 📊 Confidence scores: see how sure the model is about each segment, useful for quality control.
• 📁 Multiple formats: WAV, MP3, AIFF, AAC, OGG, FLAC, and other common audio containers are accepted.

Results export to CSV, JSON, Excel, or XML, or straight from the API.

What you can do with Audio Transcriber data

🎙️ Podcast transcriptions.

A podcast producer uploads each episode's MP3 and gets a timestamped transcript to publish as show notes, improving SEO and listener engagement.

📞 Interview analysis.

A market researcher transcribes recorded customer interviews in bulk, then runs text analysis to find recurring pain points and feature requests.

📹 Video repurposing.

A content marketer extracts the audio from a webinar recording, transcribes it, and turns the text into blog posts, quotes, and social media captions.

♿ Accessibility compliance.

An accessibility team transcribes internal training audio to create captions and transcripts that meet WCAG requirements.

📊 Call center mining.

A data analyst feeds recorded support calls through the Actor and loads the transcripts into a BI tool to track sentiment and issue frequency.

Why choose this scraper

	What you get
No API key or setup	Start transcribing on the first run, no account with a speech provider needed
Flat, predictable output	One record per audio file with the full text, timestamps, and metadata
Works with common formats	WAV, MP3, AIFF, AAC, OGG, FLAC, and more are accepted without conversion
Language hint for accuracy	Pass an ISO code to reduce misheard words in accented or technical speech

How it compares

This Actor focuses on audio files only, while the competitors below target video platforms or offer broader video-to-text pipelines.

Feature	ParseForge	Instagram Transcript API & Profile Scraper - AI Video to Text	Video Transcript
Accepts direct audio file upload	Yes	Not listed	Yes
Accepts public audio URL	Yes	Not listed	Yes
Returns timestamped segments	Yes	Yes	Yes
Returns confidence scores	Yes	Not listed	Not listed
Language hint input	Yes	Not listed	Not listed
Supports Instagram Reels	No	Yes	Not listed
Supports video files	No	Yes	Yes

Configure the run

Drive the Actor with one or more audio file URLs, or upload files directly in the Apify console. Set an optional language code to improve accuracy, and the Actor returns one transcript record per file. The Input tab lists every parameter.

A first run with the defaults:

{
 "audioFileUrl": [
 "https://upload.wikimedia.org/wikipedia/commons/e/e9/Mia_Love_speaks_in_opposition_to_the_Joint_Comprehensive_Plan_of_Action.ogg"
 ],
 "language": "en"
}

Pricing

Pay-per-result: $0.44 per result collected. You pay only for the results written to your dataset.

Results collected	Approximate cost
100 results	$44.00
1,000 results	$440.00
10,000 results	$4400.00

New Apify accounts start with $5 in free credit.

Free users

Free-plan runs return up to 10 results as a preview. Upgrade your Apify plan to collect up to 1,000,000 results per run.

Run it

1. Create a free Apify account with $5 in credit.
2. Open the Audio Transcriber - Speech to Text.
3. Set your inputs and any filters, then click Start.
4. Export the results as CSV, Excel, JSON, or XML from the Dataset tab.

Run it programmatically through the Apify API (run-sync-get-dataset-items) or the ApifyClient for JavaScript and Python.

Use with AI agents (MCP)

Give an AI agent live access to Audio Transcriber through the Model Context Protocol. Add the Actor to Claude, Cursor, or any MCP client:

$claude mcp add --transport http apify "https://mcp.apify.com?tools=parseforge/audio-transcriber"

Then prompt it in plain language to run the scraper and read back the results.

Troubleshooting

Why am I getting no results?

Check that the audio file URL is publicly accessible and returns a valid audio file. If you uploaded a file, make sure it is not corrupted and is in a supported format.

The transcript is inaccurate or has many wrong words.

Set the language input to the correct ISO 639-1 code for the audio. Also ensure the audio quality is decent; background noise or heavy accents can reduce accuracy.

The run fails with a timeout or memory error.

The audio file may be too large. Try splitting it into smaller segments or compressing it to a lower bitrate MP3 before uploading.

I get an error about unsupported file format.

Convert the file to MP3 or WAV using a tool like ffmpeg or an online converter, then run the Actor again.

The output is missing timestamps or confidence scores.

Ensure you are using the latest version of the Actor. If the issue persists, check the raw output in JSON format; some fields may be nested under a segments array.

FAQ

Question	Answer
What audio formats does this Actor support?	It accepts WAV, MP3, AIFF, AAC, OGG, FLAC, and other common audio containers. If your file is in a less common format, convert it to MP3 or WAV first.
Can I transcribe a file from a URL?	Yes. Provide a publicly accessible URL to the audio file in the audioFileUrl input field. The Actor downloads and processes it automatically.
Can I upload a file directly instead of using a URL?	Yes. In the Apify console, use the file upload editor for the audioFileUrl field to attach a local audio file. It will be processed the same way.
How do I improve accuracy for a specific language?	Set the language input to the ISO 639-1 code for the audio's language, such as 'en' for English or 'es' for Spanish. This helps the model choose the right vocabulary and pronunciation.
Does the Actor return timestamps?	Yes. Each transcript segment includes start and end times, so you can locate exact moments in the audio.
Is there a limit on file size or duration?	The Actor can handle files up to the Apify platform's upload limit, which is typically hundreds of megabytes. For very long recordings, consider splitting the audio into smaller chunks.
What does the output look like?	You get one record per audio file, with fields for the full transcript text, segment-level timestamps, detected language, and confidence scores. You can export to JSON, CSV, Excel, or XML.
Can I transcribe multiple files in one run?	Yes. Pass an array of URLs in the audioFileUrl field, and the Actor will process each one and return a separate record for each.
Does this Actor work with video files?	No, this Actor is designed for audio files. If you have a video, extract the audio track first, or use a video transcript Actor like Video Transcript.
Is my audio data stored after the run?	Apify stores the input and output for the duration of your run history, but you can delete runs at any time. The audio file itself is not retained after processing unless you keep the run.

Related actors

Browse the full ParseForge collection for more scrapers.

🆘 Need help? Email parseforge@protonmail.com with your run ID, your input, and what you expected.

⚠️ Disclaimer. This Actor is unofficial and is not affiliated with, endorsed by, or sponsored by Apify. It collects only publicly available data. You are responsible for using the collected data in compliance with the source's terms of service and applicable data-protection laws, including GDPR, CCPA, and PIPL. Do not use it to collect personal data unlawfully.