Transcription

Free Audio to Text Converter

Upload an audio or video file and SpeakScribe transcribes it with Whisper large-v3-turbo into a clean transcript, a timestamped version and SRT/VTT subtitles. Choose from 99 languages or let it detect the language. Free to try, no account required.

New uploads are paused until it finishes, so the service stays fast for everyone. You can leave this page — the result will be waiting in your queue.

Open my queue →

MP3, M4A, WAV, FLAC, OGG, MP4 · up to 20 MB as a guest

Transcribing your audio…

How accurate is each language? Tested

We transcribed 20 recordings per language from Google's FLEURS dataset — native speakers reading news-style sentences — with the same Whisper large-v3-turbo setup this tool uses, on 30 October 2026, and checked every transcript against what was said. Best results first.

LanguageWhat to expect
Italian Quick read-through
Spanish Quick read-through
German Quick read-through
Portuguese Quick read-through
Korean Quick read-through
Turkish Quick read-through
Russian Quick read-through
Dutch Quick read-through
Polish Quick read-through
French Quick read-through
Malay Quick read-through
Ukrainian Quick read-through
Filipino Quick read-through
Indonesian Quick read-through
Japanese Quick read-through
Kazakh Quick read-through
English Quick read-through
Arabic Quick read-through
Vietnamese Quick read-through
Chinese Quick read-through
Swahili Light editing
Persian Light editing
Urdu Moderate editing
Hebrew Moderate editing
Hindi Moderate editing
Thai Moderate editing
Kannada Moderate editing
Tamil Heavy editing
Nepali Heavy editing
Marathi Heavy editing
Telugu Heavy editing
Bengali Heavy editing
Gujarati Not usable yet
Somali Not usable yet
Pashto Not usable yet
Punjabi Not usable yet
Malayalam Not usable yet
Amharic Not usable yet
Uzbek Not usable yet
Burmese Not usable yet

Read speech is an easy case; real interviews and phone calls produce more errors. FLEURS © Google, CC BY 4.0. How we tested

Transcribe by language

32 languages with dedicated guidance on scripts, accuracy and common errors — plus 99 in total via auto-detect.

Transcribe by file type

Every format below uploads directly — no conversion step needed.

Transcribe by situation

What is hard about each kind of recording, and a workflow that survives it.

How it works

1

Upload your audio

Drop in an MP3, M4A, WAV, FLAC, OGG, WMA or MP4 file.

2

Pick a language

Choose the language or let auto-detect handle it.

3

Get your transcript

Download the clean text and the timestamped version.

99 languages

Whisper recognises 99 languages; the guides below cover 26 of them in depth.

Timestamps and subtitles

Get a clean transcript, a timestamped version and SRT/VTT subtitle files.

Free, no signup

Transcribe as a guest instantly — no credit card required to start.

Great for

Podcasts
Interviews
Lectures & meetings
YouTube videos

What you get back

Every job returns all of these — take whichever fits the job.

Clean transcript for reading and editing
Thanks everyone for joining. Let's start with last month's numbers. I'll share my screen so you can follow along. The headline is that renewals came in ahead of forecast for the third quarter running.
Timestamped for subtitles and citation
[00:00 → 00:04] Thanks everyone for joining.
[00:04 → 00:09] Let's start with last month's numbers.
[00:09 → 00:14] I'll share my screen so you can follow along.
Subtitles .srt and .vtt
1
00:00:00,000 --> 00:00:04,000
Thanks everyone for joining.
2
00:00:04,000 --> 00:00:09,000
Let's start with last month's numbers.

An illustration of the output formats, not the result of a particular recording. Subtitle files are ready for YouTube and video editors.

Frequently asked questions

Upload your audio file above, choose a language (or auto-detect), and start. When it finishes, download the clean transcript or the timestamped one — guests can try it without signing up.
MP3, M4A, WAV, FLAC, OGG, WMA and MP4. Other video formats such as MOV or MKV need converting to MP4 first.
It depends mostly on the recording: one clear voice in a widely spoken language needs little editing, while music, overlapping speech or phone audio need more. After transcribing you can run an optional AI pass to fix spelling and punctuation.
Files are processed for your transcript and automatically deleted after the retention period for your plan (7 days on the free plan).

Do more with your content

Transcription, 361 AI voices, and YouTube SEO — all in one free creator suite.

Explore all tools