Text to speech · עברית
Hebrew text to speech (Hebrew TTS) reads everyday Hebrew aloud from ordinary text without niqqud, the vowel points that most Hebrew leaves out, with numbers and English words read in the right order inside right-to-left sentences. Add niqqud only to a word that could be read two ways. Play it free below with no login. כתבו בעברית ותשמעו מיד.
המשלוח מ-Sonex יוצא מחר ויגיע בין עשר לשתים עשרה בבוקר. השליח יתקשר לפני, ואם שעה אחרת נוחה יותר, אפשר לשנות דרך ה-app או ב-link שנשלח ב-SMS.
Voices
Free to play in your browser without an account, up to 220 characters at a time. To save the audio as a file, sign up free for 10,000 characters and one voice clone, no card required: the dashboard saves WAV and the API returns MP3.
Making a video? See AI voice-over for YouTube and Reels. The audio is yours to use on monetised channels.
Last verified 24 October 2026
There is no native Hebrew platform voice yet, so the playground uses Liz, a voice recorded in another language: the Hebrew text is read correctly, in that voice's accent. For a local accent, clone a native Hebrew speaker from a 10-second recording and use that voice for every clip.
Sign up free, then send Hebrew text to the API with "output_format": "mp3" and save the file, or generate clips in the dashboard and download them. Scripts longer than the playground's 220 characters work the same way.
About Hebrew
Hebrew is written right to left in a 22-letter alphabet, and five letters change shape at the end of a word: כ/ך, מ/ם, נ/ן, פ/ף and צ/ץ. Everyday Hebrew leaves out the vowel points (niqqud), so a word like ספר can be sefer (book), sapar (barber) or siper (told), and the reader chooses from context. Numbers, prices and Latin-script brand names run left to right inside right-to-left sentences, and a voice has to read them in the right order.
Hebrew marks gender almost everywhere, even in the first person present: a woman says אני שמחה and a man says אני שמח (I'm happy). Unpointed text often hides the difference for "you", since לך is lekha to a man and lakh to a woman, so customer messages work best when written to avoid it. Spoken Hebrew is informal and full of loans: סבבה and יאללה from Arabic, אוקיי, אפליקציה and סמס from English. Health funds, banks and couriers send constant appointment and delivery reminders, and a relaxed spoken tone suits the way Israelis actually talk on the phone.
Use cases
Appointment confirmations and test-result notices for clinics and health funds.
Courier time-window and pickup-point calls for online shops.
Payment, card and claim-status calls written in a casual, neutral style that avoids gendered forms.
Commercial use
The full wording is in our terms of service.
YouTube
Yes, AI voices are allowed. What YouTube limits is mass-produced, repetitive content: videos made from a template with little original work. Its July 2025 update renamed that rule from “repetitious” to “inauthentic” content (YouTube’s monetisation policies).
Write your own script, add your own research or editing, and keep one consistent voice for the channel. Where a realistic AI voice could mislead viewers, use YouTube’s altered or synthetic content label. The monetisation decision is always YouTube’s.
Voice cloning
Clone your voice from a 10-second recording. Your clone speaks Hebrew, and every other language Pāṇini supports, in your own voice. The language comes from the text you type, so a clone recorded in English or Hindi can read a Hebrew script.
Your accent comes with it: a clone sounds like you speaking Hebrew, not like a different native speaker. Every free account includes one voice clone. Clone only your own voice, or a voice whose owner has agreed.
API
One request returns Hebrew audio as MP3. The language is detected from the text, so no language setting is needed. Pāṇini TTS starts streaming audio in under 200 ms (time to first byte).
1curl https://api.sonexlabs.com/v1/speech \2 --header 'Authorization: Bearer YOUR_API_KEY' \3 --header 'Content-Type: application/json' \4 --data '{"text": "המשלוח מ-Sonex יוצא מחר ויגיע בין עשר לשתים עשרה בבוקר. השליח יתקשר לפני, ואם שעה אחרת נוחה יותר, אפשר לשנות דרך ה-app או ב-link שנשלח ב-SMS.", "output_format": "mp3"}' \5 --output hebrew.mp3FAQ
Yes. The playground on this page reads up to 220 characters of Hebrew at a time with no account. Sign up free for 10,000 characters and one voice clone, no card; after that it costs $0.03125 per 1,000 characters.
Yes, after free sign-up. The playground on this page plays audio in your browser only, up to 220 characters at a time, so you can check the voice first. Sign up free (10,000 characters and one voice clone, no card): the dashboard saves each clip as a WAV file with Download audio, and the API returns MP3 when you set "output_format": "mp3".
No. Pāṇini reads ordinary unpointed Hebrew. Add points only to a word that could be read two ways in your sentence.
Yes. Mixed right-to-left and left-to-right text, such as a price or an app name inside a Hebrew sentence, is read in order in one voice.
Liz reads these samples; any Sonex Labs voice can speak Hebrew, and you can clone a native speaker's voice from 10 seconds.
$0.03125 per 1,000 characters, the same as every language.
Yes. Audio you generate, on the free tier or with paid credits, can be used on monetised YouTube channels, Shorts, Reels and in ads, with no attribution. YouTube limits mass-produced, repetitive videos, not AI voices, so write your own script and keep your edits original. The monetisation decision is YouTube's.
The audio you generate is yours to use, including commercially, with no attribution and no royalties to Sonex Labs. You are responsible for the script itself: if you read someone else's text, you need their permission.
Yes. A Sonex voice clone is not tied to the language it was recorded in. Type a Hebrew script and your clone reads it in your own voice, with Hebrew pronunciation. Your natural accent carries over, so it sounds like you speaking Hebrew.
More languages
See text to speech in every language, the full list of 250+ languages, pricing, the Pāṇini TTS API, or transcribe Hebrew audio with Valmiki speech to text.
10,000 free text-to-speech characters and one free voice clone that speaks every language, no card required. Every language is billed at the same rate.