Can Perplexity Transcribe Audio Files?

Short answer: yes — but for search, not for transcripts. Perplexity (made by Perplexity AI) accepts audio and video uploads (MP3, WAV, M4A, FLAC and more, roughly 40–50MB depending on plan) and converts the speech into searchable text so you can ask questions about the recording. That is genuinely useful. But it is not a transcript-production workflow: Perplexity’s own documentation warns that for long files it may analyze only the most relevant portions rather than the whole recording, and there is no transcript editor, no word-level timestamps, no synchronized review against the audio, and no SRT/VTT/DOCX export. Files in unsupported codecs (Opus, WMA, AMR) fail outright.

When the transcript itself is the deliverable, use a dedicated tool: Jackob.ai transcribes the entire file — however long — with speaker labels and timestamps in any of 98 languages, lets you verify the text against the audio, and exports DOCX, PDF, TXT, SRT, and VTT. Free plan available, no credit card.

Drag & drop your audio or video file here

or click to browse — MP3, WAV, M4A, MP4, MOV and more

Free plan available · No credit card required · Files are never used to train AI

How it works

  1. 1

    Upload your file

    Audio or video, any common format, from any device.

  2. 2

    AI transcribes it

    Speaker labels, timestamps, automatic language detection across 98 languages.

  3. 3

    Use the output anywhere

    Documents, subtitles, plain text — including as source material for AI research tools.

Why Jackob.ai

Actual transcription

A speech-to-text engine processing your recording — not a search engine describing one.

Research-friendly outputs

Timestamped, citable transcripts — useful source material for tools like Perplexity.

98 languages

Multilingual recordings transcribed with automatic detection.

Privacy-first

Your files are never used to train AI models.

Simple, transparent pricing

Start free. Upgrade when you need more hours — no per-minute surprises.

Plus

$15/mo

20 hours of transcription per month

Pro

$29/mo

50 hours of transcription per month

Premium

$49/mo

100 hours of transcription per month

See full plan details

Your recordings stay private

Files are processed securely and are never used to train AI models. You control retention and can delete your recordings and transcripts at any time.

Frequently asked questions

What can Perplexity actually do with my recording?

Uploaded audio and video are converted to searchable text so you can ask questions about the content ("what did they say about pricing?"). For short files this covers the whole recording; for long files Perplexity’s documentation says it may extract only the most important portions. There is no full-transcript editor or export — the output lives inside the chat thread.

Can I use my transcript with Perplexity?

Yes — export TXT from Jackob.ai and use the transcript as context for research, fact-checking quotes, or follow-up questions.

What does real transcription cost?

Jackob.ai has a free plan (no credit card) and paid plans from $25/month for 10 hours of transcription.

Related

Try it with your own recording

The best way to judge transcription quality is with your own audio. Upload a real file on the free plan — no credit card required.

Get started free