Have your greeting read aloud with ElevenLabs Eleven v3
Eleven v3 is the text-to-speech model from ElevenLabs. Here it reads your greeting in one of 8 catalogue voices, in English, Russian, Hebrew or Arabic, and it gives the voice to our talking cards. For a greeting in your own voice, MiniMax Speech takes over after one short recording on a paid plan.
- Made by ElevenLabs
- 1 credit for every 5 characters
- Your own voice: 1,880 credits, once
Updated 29.09.2026
Ava, Daniel and Noa read the same line
Start from the listener, then press play
Start from the person who will listen, not from the voice you like best. The three samples above read the same line - "Happy birthday! I wish I could hug you today - this is the next best thing." - and each lands differently. Ava takes her time, Daniel says it plainly, Noa sounds as if the party has already started.
A letter to a parent wants warmth and time: Ava, or Mira, who sounds like somebody who has known them for years. A retirement or a thank-you after a hard year sits well with Daniel. Ari is grave, the one for goodbyes and the big anniversaries. For a birthday meant to be fun, try Noa or Yael; Tomer is easy and conversational, and Lena can hold a six-year-old through a long greeting.
The picker narrows it down by language, gender, age and style - warm, cheerful, calm, solemn, for a child, storytelling. Then press play. If the result sounds flat, move Stability down a little; if it sounds too theatrical for Grandpa, move it up.
Savta in Hebrew, the cousins in English, one voice
Eleven v3 covers Hebrew, and that matters here. A family in Haifa, Nazareth or Rishon LeZion gets a greeting in the language they speak at the table, not a translation. Mira can wish Savta a happy birthday in Hebrew and read the English card for the cousins in London in the same voice.
Write the greeting in the language it should be heard in, or ask the agent to write it that way - the voice reads what is on the page. Names are where any voice is most likely to trip: if Dedushka or Teta comes out wrong, spell it the way it sounds and make it again.
Accent is for English only. American, British, Australian and Indian change how an English greeting sounds; for Hebrew, Arabic and Russian it does nothing. Length is yours. The agent keeps a spoken greeting to 20-60 words, while Standard takes up to 2,500 characters - enough for a long letter to a parent far away. The price grows with the text and is on the button before you press.
When a voice alone is enough, and when it is not
Eleven v3 reads. It does not sing and it does not show a face, which makes the choice simple. When the words matter most and the listener has the phone to their ear - on a drive, in a hospital bed, at the kitchen table with their glasses in the other room - a voice greeting is the whole thing, and it costs less than a talking card.
When the face matters, make a talking card: the same voice, with Kling AI Avatar v2 moving the face and head of someone in a photo, or OmniHuman 1.5 moving the whole person. The grandmother on our talking-card page speaks with Ava's voice. For a song, Google Lyria 3.5 sings lyrics you approve first. For a video with voices in it, Veo 3.1 makes that sound in the same generation.
Your own voice is the last step up. On a paid plan you read a short passage shown on screen, tick the box to confirm it is yours, and MiniMax Speech 02 HD makes it. The recording is not kept, and you can delete the voice whenever you like.
Two true details and a voice to match
A voice greeting for my dad Mark's 60th birthday. He taught me to drive in his old blue Volvo and never once raised his voice, even when I hit the gate. Warm and a little funny, read by a calm male voice.
A voice greeting in Hebrew for my grandmother Rivka's 85th birthday. Tell her I still bake her apple cake every Friday and that I am coming to Haifa for Passover. Gentle and warm.
A voice greeting for my daughter Maya's 6th birthday, bright and silly. Mention the dinosaur cake in the fridge, her new red bike, and that Grandpa is coming on Saturday to teach her to ride it.
Eight ready voices, or the one your family knows
Eleven v3 reads greetings in the 8 catalogue voices on any plan, with Accent, Stability and Effect. MiniMax Speech 02 HD reads in your own voice after one recording, on Plus, Family and Pro, and only the Effect applies to it.
| Model | Strong at | Price |
|---|---|---|
| Eleven v3ElevenLabs | Natural voices, Hebrew included | 1 credit for every 5 characters |
| MiniMax Speech 02 HDMiniMax | Your own voice | Your own voice: 1,880 credits, once |
Prices are in credits and are always shown on the button before you press it. Pricing
Write it, pick who reads it, listen once
- 1
Tell the agent, or type the words
In the chat, say who it is for and what the day is. The agent asks a few questions with buttons, then writes 20 to 60 words meant to be heard - the text is free. Or switch to Standard, choose Voice and paste your own words, up to 2,500 characters.
- 2
Choose whose voice
When the agent asks whose voice should read it, tap Pick a voice; in Standard, open the voice picker. Our voices lists all eight, each with a play button, and Your own holds the voice you recorded. In Standard, set the accent, stability and effect right next to it.
- 3
Press the button, listen, send
The price is on the button - Read it aloud in the chat, Generate in Standard - and nothing is charged before you press. Listen; if a line sits wrong, change it and make it again. Then send it by email, SMS or a messenger, now or scheduled for the day.
Keep exploring
An AI voice greeting is your written greeting turned into a voice message they can play on speaker, in the…
OpenTalking photo cardA talking photo card has someone you love say your greeting out loud - up to 15 seconds of speech,…
OpenLyriaLyria 3.5 is Google's music model, and on Wish Generator it makes every song. You tell us who it is…
OpenVoices, accents and Hebrew: your questions
Eleven v3 is the text-to-speech model from ElevenLabs: it turns written words into natural speech. On Wish Generator it reads voice greetings in 8 catalogue voices - Ava, Noa, Daniel, Mira, Tomer, Lena, Ari and Yael - in English, Russian, Hebrew or Arabic, and it gives the voice to our talking cards.
Yes. Eleven v3 reads Hebrew, and here it is the model behind the catalogue voices. Write the greeting in Hebrew, or ask the agent to, pick a voice and press the button. Filter the voice picker by Hebrew to see the voices tagged for it, and hear each one before you choose.
Yes. A talking card speaks in the same catalogue voices, read by Eleven v3, or in your own voice if you have recorded one. Kling AI Avatar v2 moves the face and head of the person in the photo, OmniHuman 1.5 moves the whole person, and either way the card holds up to 15 seconds of speech. The grandmother on our talking-card page speaks with Ava's voice.
Yes, with a paid plan - Plus, Family or Pro - though that voice is made with MiniMax, not ElevenLabs. You read a short text aloud once in the browser, MiniMax Speech 02 HD builds your voice, and you pay once in credits. Then voice greetings and talking cards can speak as you. On the free plan, use the 8 ElevenLabs voices.
Up to 2,500 characters when you paste your own text in Standard - enough for a proper letter. The agent in the chat writes 20 to 60 words, because a spoken greeting is easier to take in when it is brief. A talking card is shorter still: up to 15 seconds of speech.
Yes. For an English greeting, Accent switches between American, British, Australian and Indian. Stability runs from expressive to steady. Effect adds Studio, Warm room or Phone call to the finished recording, on our server, at no extra cost. With your own voice, only the Effect applies.
Eight voices, and one of them is right for Dad
Write the words, choose from eight voices or your own, and let it arrive on the day.
Pick an Eleven v3 voice
