# Video to Text

> [Video to Text](https://video2text.net) is an AI-powered transcription service that converts video and audio files into clean, exportable text. It supports 99 languages, speaker diarization, timestamps, and multiple export formats (SRT, VTT, TXT, CSV). New users get 30 free credits. Pricing is pay-as-you-go with no subscription.

Video to Text is built for creators, teams, and individuals who need fast, accurate speech-to-text conversion without maintaining their own transcription pipeline.

Key facts:
- Supports audio formats: `.aac`, `.flac`, `.m4a`, `.mp3`, `.oga`, `.ogg`, `.opus`, `.wav`
- Supports video formats: `.mp4`, `.m4v`, `.mov`, `.mkv`, `.webm`
- Maximum file size: 5 GB; maximum media duration: under 10 hours
- Transcription speed: RTF of 0.008x (e.g. a 1h 3m meeting completes in ~35 seconds)
- Export formats: `csv`, `srt`, `vtt`, `txt`
- 30 free credits for new users; pay-as-you-go after that
- 14-day refund policy for unused credits

---

## How to Use Video to Text

Source: https://video2text.net/docs/how-to-use-video-to-text

How to use Video to Text is straightforward: sign in, upload a supported file, choose your language settings, wait for transcription, and export the result in the format you need.

### Step 1: Sign in and prepare your credits

Before you start a transcription, sign in to your account. The app checks account access and available credits before it begins processing.

New users receive **30 free credits**. If your remaining credits are not enough for the file you selected, the app prompts you to top up before transcription starts.

### Step 2: Upload a supported audio or video file

Click the upload area and choose your file.

Video to Text currently accepts these file types:

- Audio: `.aac`, `.flac`, `.m4a`, `.mp3`, `.oga`, `.ogg`, `.opus`, `.wav`
- Video: `.mp4`, `.m4v`, `.mov`, `.mkv`, `.webm`

Upload limits:
- Maximum file size: **5 GB**
- Maximum media duration: **under 10 hours**

If your file breaks either limit, the app stops the workflow before transcription begins.

### Step 3: Choose your language option

After selecting a file, choose the language setup that matches your recording:

- Pick a specific language if you know it
- Use **auto detection** if you are not sure
- Use **multilingual detection** if the recording switches between languages

### Step 4: Turn on speaker labels if you need them

Speaker labels are useful for conversations with more than one person. When enabled, the transcript separates content by speaker. Useful for meetings, interviews, panel discussions, and classroom recordings.

### Step 5: Wait for upload and transcription to finish

Once you submit the file, the app uploads it to storage and then starts transcription. Progress messages appear while the job is running.

Total time depends on: file duration, upload speed, file size, and audio clarity.

### Step 6: Export the transcript

When transcription is complete, the app takes you to the export page. Export formats:

- `csv` — for spreadsheet review or structured handoff
- `srt` — for subtitles (timed)
- `vtt` — for subtitles (web standard)
- `txt` — for plain text editing and note-taking

### Quick workflow summary

1. Sign in.
2. Upload a supported file (under 5 GB, under 10 hours).
3. Pick a language option (specific, auto, or multilingual).
4. Turn on speaker labels if needed.
5. Start transcription.
6. Export the finished transcript in `csv`, `srt`, `vtt`, or `txt`.

---

## Supported Media Formats for Video to Text

Source: https://video2text.net/docs/video-to-text-supported-media-formats

### Supported audio formats

- `.aac`
- `.flac`
- `.m4a`
- `.mp3`
- `.oga`
- `.ogg`
- `.opus`
- `.wav`

These formats cover most voice notes, podcasts, interviews, lectures, and exported audio tracks from editing tools.

### Supported video formats

- `.mp4`
- `.m4v`
- `.mov`
- `.mkv`
- `.webm`

### Upload limits

- **Maximum file size:** 5 GB
- **Maximum media duration:** less than 10 hours

### Which format should you choose?

- Choose **MP3** or **M4A** for spoken audio when you want smaller files.
- Choose **WAV** or **FLAC** when you want lossless audio.
- Choose **MP4** for video in most cases because it is widely supported.
- Keep the file as close to the original recording as possible. Re-encoding a file several times can lower speech clarity.

---

## Supported Languages in Video to Text

Source: https://video2text.net/docs/video-to-text-supported-languages

Video to Text supports **99 languages** for speech transcription. You can choose a specific language, let the app detect the language automatically, or use multilingual detection when the recording switches between languages.

### Language selection modes

- **Manual selection** — choose a specific language before uploading
- **Automatic language detection** — the app detects one language automatically
- **Multilingual detection** — the app handles recordings that switch between languages

### Full supported language list

- Afrikaans (`af`)
- Albanian (`sq`)
- Amharic (`am`)
- Arabic (`ar`)
- Armenian (`hy`)
- Assamese (`as`)
- Australian English (`en_au`)
- Azerbaijani (`az`)
- Bashkir (`ba`)
- Basque (`eu`)
- Belarusian (`be`)
- Bengali (`bn`)
- Bosnian (`bs`)
- Breton (`br`)
- British English (`en_uk`)
- Bulgarian (`bg`)
- Burmese (`my`)
- Catalan (`ca`)
- Chinese (`zh`)
- Croatian (`hr`)
- Czech (`cs`)
- Danish (`da`)
- Dutch (`nl`)
- Estonian (`et`)
- Faroese (`fo`)
- Finnish (`fi`)
- French (`fr`)
- Galician (`gl`)
- German (`de`)
- Global English (`en`)
- Georgian (`ka`)
- Greek (`el`)
- Gujarati (`gu`)
- Haitian (`ht`)
- Hausa (`ha`)
- Hawaiian (`haw`)
- Hebrew (`he`)
- Hindi (`hi`)
- Hungarian (`hu`)
- Icelandic (`is`)
- Indonesian (`id`)
- Italian (`it`)
- Japanese (`ja`)
- Javanese (`jw`)
- Kannada (`kn`)
- Kazakh (`kk`)
- Khmer (`km`)
- Korean (`ko`)
- Lao (`lo`)
- Latin (`la`)
- Latvian (`lv`)
- Lingala (`ln`)
- Lithuanian (`lt`)
- Luxembourgish (`lb`)
- Macedonian (`mk`)
- Malagasy (`mg`)
- Malay (`ms`)
- Malayalam (`ml`)
- Maltese (`mt`)
- Maori (`mi`)
- Marathi (`mr`)
- Mongolian (`mn`)
- Nepali (`ne`)
- Norwegian (`no`)
- Norwegian Nynorsk (`nn`)
- Occitan (`oc`)
- Panjabi (`pa`)
- Pashto (`ps`)
- Persian (`fa`)
- Polish (`pl`)
- Portuguese (`pt`)
- Romanian (`ro`)
- Russian (`ru`)
- Sanskrit (`sa`)
- Serbian (`sr`)
- Shona (`sn`)
- Sindhi (`sd`)
- Sinhala (`si`)
- Slovak (`sk`)
- Slovenian (`sl`)
- Somali (`so`)
- Spanish (`es`)
- Sundanese (`su`)
- Swahili (`sw`)
- Swedish (`sv`)
- Swiss German (`de_ch`)
- Tagalog (`tl`)
- Tajik (`tg`)
- Tamil (`ta`)
- Tatar (`tt`)
- Telugu (`te`)
- Thai (`th`)
- Tibetan (`bo`)
- Turkish (`tr`)
- Turkmen (`tk`)
- Ukrainian (`uk`)
- Urdu (`ur`)
- US English (`en_us`)
- Uzbek (`uz`)
- Vietnamese (`vi`)
- Welsh (`cy`)
- Yiddish (`yi`)
- Yoruba (`yo`)

---

## How Long Does Video to Text Take?

Source: https://video2text.net/docs/how-long-does-video-to-text-take

How long Video to Text takes depends on both upload time and transcription time. The transcription engine uses a **real-time factor (RTF) of 0.008x**, meaning transcription is much faster than the original media length.

### Timing benchmarks

| Recording type | Media length | Example completion time |
| -------------- | ------------ | ----------------------- |
| Meeting        | 1h 3m        | 35 seconds              |
| Podcast        | 3h 15m       | 133 seconds             |
| Video course   | 8h 21m       | 300 seconds             |

### What affects total wait time?

1. **Upload speed** — the file must be uploaded before transcription begins; slow connections add time, especially for large video files
2. **File duration** — longer recordings take longer, though the transcription stage is still much faster than real time
3. **File size and format** — video files are often larger than audio-only files, making upload the main delay
4. **Audio clarity** — background noise, overlapping speakers, and mixed-language content can slow processing

### Tips for faster results

- Upload audio instead of video when you only need the transcript
- Use a stable connection before starting the upload
- Trim unnecessary intros, outros, or blank sections
- Choose the correct language option instead of relying on auto-detection

---

## Pricing

Video to Text uses a pay-as-you-go model with no monthly subscription.

- **Free:** 30 credits for new users upon sign-up
- **Lite:** $9.9 / 200 credits
- **Pro:** $19.9 / 600 credits
- **Ultra:** $99 / 6000 credits

A **14-day refund policy** applies to unused credits.

If your available credits run out mid-session, the app prompts you to top up before transcription starts.

You can check the [price page](https://video2text.net/pay) for more details and buy credits.

---

## Common Use Cases

- **Content creators** — generate subtitles for YouTube, social media, or course videos
- **Knowledge workers** — convert meeting recordings into structured notes
- **Journalists** — transcribe interview audio quickly
- **Students** — turn lecture recordings into study notes
- **Teachers** — transcribe educational videos for accessibility
- **Language learners** — get text from audio to support listening and reading practice

## About the creator

Video to Text is built by [Dkphhh](https://www.dkphhh.me), a solo indie developer. Other tools by the same creator:

- [Read PDF Aloud](https://readpdfaloud.com/)
- [Send to Feishu](https://dkphhh.me/tools/send-to-feishu/)
- [Glitch Text Generator](https://cooltext.app/)