Transcribe audio to text

Convert audio and video into accurate text, AI summaries, notes and chat.

Add audio or videoDrag files here or click to chooseTap to choose audio or video MP3, WAV, M4A, MP4 and moreChoose files

Add more files

Step 1Upload a file, record audio or paste a link
Step 2AI transcribes your recording
Step 3Get text with speakers and word timestamps

My files

File nameDate DurationStatus
70+languages
5 AI modelsup to 3 h · 1 GB
AI summaries6 reports & chat
TXT · DOCX · SRTand 5 more formats

How to transcribe audio to text

  1. Add your recording

    Upload one or more files (up to 100 at once), record with your microphone or paste a link.

  2. Choose a model and language

    Select a model for speed or accuracy. Choose the recording language or let the model detect it. You see the price in credits before you start.

  3. Summarize, chat and export

    Listen and read along, generate AI summaries or meeting notes in one click, ask questions in the AI chat, and download TXT, DOCX, PDF, SRT or VTT.

↑ Transcribe a file — scroll up

Audio to text transcription online

Convert audio and video into accurate text, summaries, notes and actionable insights.

Speaker labels · Word timestamps · AI summaries & chat · 70+ languages · TXT · DOCX · SRT

Choose from five transcription models, chat with your recordings and export in any format. Upload audio (MP3, WAV, M4A, OGG, FLAC and more) or video (MP4, MOV, MKV, AVI, WEBM) up to 3 hours and 1 GB, record your voice or paste a YouTube, Google Drive or direct file link. Everything runs in the browser on a computer or a phone — nothing to install.

What your transcript looks like

One recording with two speakers, exported to four formats: plain text, a document and two subtitle files. Your file gets the same structure.

TXT
[00:01] Speaker 1: 


[00:05] Speaker 2: 

DOCX
Speaker 1 00:01

Speaker 2 00:05

SRT
1
00:00:01,200 --> 00:00:04,500



2
00:00:05,100 --> 00:00:08,300
VTT
WEBVTT

00:00:01.200 --> 00:00:04.500
<v Speaker 1>


00:00:05.100 --> 00:00:08.300
<v Speaker 2>

Subtitle lines are 42 characters by default. You can change this before you download.

AI summaries, meeting notes and chat with your recording

Go beyond a raw transcript. Generate structured reports in one click or ask questions in the built-in AI chat — every answer is based on your recording, with clickable timestamps.

  • Brief summary

    Get the main topic, key decisions, numbers, dates and responsible people in 3 to 5 sentences.

  • Detailed notes

    Structured notes grouped by topic: context, discussion points, arguments, decisions and open questions.

  • Decisions and action items

    Confirmed tasks with owner, deadline and exact quote [MM:SS], separated from items that still need clarification.

  • Minutes with verifiable quotes

    Formal meeting minutes where every statement is backed by a verbatim quote, speaker name and timestamp.

  • Key takeaways

    The main ideas and conclusions from a lecture, podcast, interview or webinar, each linked to a timestamp.

  • Chapters for YouTube

    Topic-based video chapters starting at 0:00 with clickable timestamps, ready to paste into a YouTube description.

AI chat with your recording: use quick prompts ("What is it about?", "Key takeaways", "Quick summary", "What needs to be done?") or ask your own question in any language. Click any [MM:SS] timestamp in the answer to hear that moment, and download any report as PDF, DOCX or TXT.

What the transcript generator does

5 AI models

Choose Fast, Accurate, Balanced, Enhanced or Standard. Each shows its price per minute and file limit before you start.

Speaker labels

Each speaker gets a label. Rename a speaker once and the name changes in the whole transcript. Move a segment to another speaker.

Word timestamps

Click a word to play the audio from that point. The current word is highlighted during playback.

70+ languages

With regional variants of English, Spanish, Arabic and other languages. Most models can detect the language automatically.

Record with your microphone

Record in the browser, pause and resume, then send the finished recording. For voice notes, use voice to text in the browser.

Video and links

Upload a video file or paste a YouTube or Google Drive link. The audio is extracted automatically.

Preview the first minute

For files longer than 30 minutes, transcribe only the first minute to check the quality. Then transcribe the whole file.

Transcribe again

Not happy with the result? Run it again with another model or language. You see the price before you confirm.

Batch work: up to 100 files per upload and up to 20 files per export — enough for an interview series or a semester of lectures.

Speech to text models

Each model has its own strengths and price. Not sure which to pick? Start with Fast, or transcribe the first minute with two models and compare.

ModelBest forAccuracySpeedLanguagesDetects languageFile limitPrice
FastMicrosoft FastThe quickest results and the longest language list. Costs twice as much per minute.76Yes3 h / 1 GB278 credits/min
AccurateMAI-Transcribe-2High accuracy for interviews, lectures and meetings. Shorter file limit.57Yes2 h / 300 MB139 credits/min
BalancedGrok Voice Transcribe 2.0High accuracy at a medium speed. Suits long recordings up to 3 hours.25Yes3 h / 1 GB139 credits/min
EnhancedMicrosoft LLM SpeechSpeech recognition with a built-in language model for the most common languages.—24Yes3 h / 1 GB139 credits/min
StandardWhisper (Microsoft Azure)Works with the full language list. Select the language yourself. Slower than other models.76Manual3 h / 1 GB139 credits/min

Prices are in credits from your SpeechGen balance. The exact amount for your file is shown before you start.

Export to TXT, DOCX, PDF and subtitles

Documents

TXTDOCXPDF

Subtitles

SRTVTTSUB

Data

CSVJSON

Clipboard

Copy text
Paragraphs
Auto, or 1 to 8 lines per paragraph. A new paragraph starts after a pause; set the pause length (700 ms by default).
Timestamps
Add them to paragraphs, to phrases, to both, or leave them out.
Speakers
Show speaker names or hide them. Join consecutive lines of the same speaker.
Subtitle lines
Set characters per line (42 by default) and words per line.
Text only
Remove timestamps and speaker names to get clean text for a document or an AI tool.

Transcription in 70+ languages

70+ languages · 130+ regional variants · automatic language detection

English, Spanish, Portuguese, French, German, Italian, Japanese, Korean, Hindi, Arabic, Turkish and 60+ more. Pick the recording language or let the model detect it — speech to text in Spanish, German or Arabic works the same way. The list depends on the model: Fast and Standard support the most languages.

What people transcribe

  • Journalists and researchers

    Get interview quotes with the speaker and exact time, or generate minutes backed by verbatim quotes.

  • Students and teachers

    Turn lectures and seminars into structured study notes, key takeaways and searchable text.

  • Podcasters and video creators

    Get show notes, key takeaways, YouTube chapters with timestamps and SRT/VTT subtitles from one upload.

  • Business meetings

    Turn calls and meetings into a brief summary, a table of decisions and action items, or full meeting minutes.

  • Subtitle creators

    Download SRT or VTT and adjust line length. Working from a video file? Use video transcription.

  • Translators

    Start from an accurate source text in the original language.

Price per minute of audio

Transcription is paid with credits from your SpeechGen balance — the same balance you use for text to speech. Most models cost 139 credits per minute of audio; Fast costs 278. The price for your file is shown before you start, and if a transcription fails, the credits are refunded.

139credits / minAccurate · Balanced · Enhanced · Standard
278credits / minFast
See prices

Privacy and file storage

Encrypted transfer
Files and transcripts are sent over HTTPS (TLS).
Storage period
With an account, files and transcripts are kept for 90 days. Without an account — for 1 day. You can delete a file at any time.
Private results
Only you can open your results: through your account, or in the same browser if you have no account. A link alone does not give access. To share a transcript, download it and send the file.

Transcription FAQ

How accurate is the transcription?

Accuracy depends on the audio and the model. Clear speech from one or two speakers gives the best results. Background noise, music, overlapping voices, strong accents and phone-quality audio cause more mistakes. Always check names and numbers before you publish.

How long does it take?

It depends on the file length, the model and the current queue. You can close the page: the transcript is saved in your files and appears when it is ready.

Can I convert MP3, M4A or WAV to text?

Yes. Audio and video files up to 1 GB and 3 hours (the Accurate model: up to 300 MB and 2 hours). Common formats: MP3, WAV, M4A, OGG, FLAC, AAC, MP4, MOV, MKV, AVI, WEBM. You can also paste a YouTube link, a public Google Drive link or a direct link to a file.

Which languages are supported?

More than 70 languages, many with regional variants. Most models detect the language automatically; with the Standard model, you select it yourself. If your recording has a rare language, transcribe the first minute to check the quality.

How much does it cost?

You pay with credits from your SpeechGen balance, per minute of audio. The price depends on the model and is shown before you start.

Can I edit the transcript?

You can rename speakers, move a segment to another speaker and delete segments. To correct the words, download DOCX or TXT and edit the file in your text editor.

How long are my files stored, and who can see them?

With an account — 90 days, without an account — 1 day. You can delete a file earlier. Only you can open the result page; to share a transcript, download it and send the file.

Do I need to install an audio to text converter?

No. It works in the browser on a computer or a phone. Upload a file, record your voice or paste a link.

Which model should I choose?

Start with Fast for most recordings. For interviews and lectures where every word matters, try Accurate. If your language is not in the list, use Standard and select the language yourself.

How do AI summaries and chat with the recording work?

After full transcription, open the AI tab to generate a brief summary, detailed notes, action items, meeting minutes with quotes, key takeaways or YouTube chapters. You can also ask questions in the AI chat — every answer is based on your transcript with clickable [MM:SS] timestamps, and reports can be downloaded as PDF, DOCX or TXT.

Try it on your own recording

Upload a file, record your voice or paste a link. You see the price before you start.

  • No software to install
  • Up to 3 hours per file
  • Credits refunded if a transcription fails

Transcribe in full?

Delete this file?

The file and its transcript will be deleted. This cannot be undone.

Choose a language

We use cookies to ensure you get the best experience on our website. Learn more: Privacy Policy

Accept Cookies