# Hebrew speech-to-text API (עברית)

> KolWrite transcribes Hebrew audio and video through one REST call: send the file URL with "language": "he" and read back right-to-left Hebrew text in segments with word timings and speaker labels, as JSON, TXT or SRT. The Oracle models can also translate the Hebrew into English or any of 100 languages in the same job.

Last updated: 2026-10-08 · HTML: https://console.kolwrite.com/speech-to-text/hebrew

## Transcribe Hebrew with one request

Set `language` to `he` and start a job. Poll `GET /transcribe/{jobId}` for the result, or pass a `webhook_url`.

```bash
curl https://app.kolwrite.com/transcribe \
  -H "x-api-key: $KOLWRITE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"audio_url": "https://example.com/interview-he.m4a", "model": "oracle", "language": "he", "include_diarization": true, "output_format": "json"}'
```

Translate Hebrew audio into English in the same job (Oracle models only):

```bash
curl https://app.kolwrite.com/transcribe \
  -H "x-api-key: $KOLWRITE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"audio_url": "https://example.com/interview-he.m4a", "model": "oracle_mini", "language": "he", "translate_to": "en", "output_format": "srt"}'
```

## Hebrew at a glance

| Property | Details |
| --- | --- |
| API code | `he` |
| Native name | עברית |
| Writing direction | Right to left |
| Automatic detection | Yes: omit `language` or send `"auto"` |
| Translate Hebrew audio into | Any of the 100 supported languages, on Oracle models |
| Translate other languages into Hebrew | Yes: `translate_to: "he"` on Oracle models |
| Output | JSON (segments, word timings, speakers), TXT, SRT |
| Price | US$0.48 (Base) to US$3.60 (Oracle Max) per audio hour; US$1.44 on Oracle |

## What to know about Hebrew transcription

- Hebrew is written right to left. The API returns plain Unicode text with no direction marks, so set `dir="rtl"` (or `dir="auto"`) wherever you display it.
- Everyday Hebrew is written without vowel points (niqqud). Build search and matching for unpointed spelling, and strip niqqud from any reference text before you compare it with a transcript.
- Israeli speech mixes in English product names, acronyms and numbers. On mixed recordings, send `language: "he"` explicitly instead of relying on auto-detection, which decides on the dominant language.
- SRT files with Hebrew lines that end in punctuation or Latin words can render in the wrong order in players without bidirectional text support. Test your player, or add a right-to-left mark (U+200F) at the start of each cue when you post-process.

## Where teams use Hebrew transcription

- Call and meeting recordings for Israeli companies, with speaker labels for who said what.
- Lectures and seminars at Israeli universities, published as Hebrew subtitles (`srt`).
- Journalism and podcast interviews, translated to English for international editors with `translate_to: "en"`.
- Municipal, council and committee meeting minutes.

## Choosing a model

Start with `oracle` (US$1.44 per hour) for production Hebrew audio. Use `base` (US$0.48) for clean, single-speaker recordings at volume, `oracle_mini` (US$0.96) for the cheapest translation, and `oracle_pro` or `oracle_max` for noisy or difficult audio. KolWrite does not publish a Hebrew accuracy figure for this API, so test a sample of your own recordings before committing. Full comparison: [models and prices](https://console.kolwrite.com/models).

## Questions and answers

### Can KolWrite transcribe Hebrew mixed with English?

Yes. Send `language: "he"` so the recording is treated as Hebrew; English words and names inside it are transcribed as they are spoken. Check proper nouns in your own recordings, because spelling of foreign names in Hebrew script varies.

### Is the Hebrew output right to left?

The text is ordinary Unicode Hebrew. Direction is decided by whatever displays it: use `dir="rtl"` in HTML, and a right-to-left aware subtitle player for SRT.

### Can I get the Hebrew transcript and an English translation?

Translation replaces the output text with the target language. Run one job with `language: "he"` for the Hebrew transcript and one with `translate_to: "en"` on an Oracle model for the English version.

## Related pages

- [Arabic speech-to-text](https://console.kolwrite.com/speech-to-text/arabic)
- [Yiddish speech-to-text](https://console.kolwrite.com/speech-to-text/yiddish)
- [English speech-to-text](https://console.kolwrite.com/speech-to-text/english)
- [Universities & students](https://console.kolwrite.com/use-cases/education)
- [Call centers & sales calls](https://console.kolwrite.com/use-cases/call-centers)
- [Supported languages](https://console.kolwrite.com/languages/)

---
Get an API key: https://console.kolwrite.com/auth · API documentation: https://console.kolwrite.com/public_api_docs · llms.txt: https://console.kolwrite.com/llms.txt