Turn any text into natural, human-sounding speech. 60+ voices, 30+ languages and multi-speaker dialogue, powered by ElevenLabs models. Free to start, no card needed.
Free credits on sign-up · no card needed · Turbo costs 3 credits per 1,000 characters
Faceless channels, explainers and shorts. Pick a voice that fits the niche and re-generate a line in seconds.
Multilingual v2 keeps a steady, natural tone across long chapters. Bedtime stories, fiction, non-fiction.
Intros, ad reads and full episodes. Dialogue mode gives each host a different voice in one file.
Course narration in 30+ languages without booking a studio or re-recording every time the script changes.
Energetic announcers, calm explainers, friendly support agents — test several reads before you commit.
Villains, cowboys, radio DJs and narrators. Emotion tags like [whispers] and [laughs] in dialogue mode.
Up to 5,000 characters per generation, in any of 30+ languages.
Play any of 60+ voice previews before you spend a credit.
An MP3 is ready in seconds. You are only charged when it is.
Credits, not seats. 1,000 characters costs 3 credits on Turbo, 6 on Multilingual. Buy a one-time pack that never expires, or subscribe for the lowest rate.
Credits never expire. One-time purchase, no subscription.
Small
$4.9
100 credits
Enough to finish what you started
Medium
$12.9
300 credits
Large
$39
1,000 credits
Best value without committing to a plan
Credits from a pack never expire, so we don't refund packs on request. Plans can be refunded in full within 3 days of your first payment. And if we ever suspend your account, we refund everything you paid — you don't have to ask.
Yes, free to start. A new account gets 18 credits with no card — about 6,000 characters on the Turbo model. Paid plans start at $9.9/month and include commercial usage rights.
Per 1,000 characters: 3 credits on Turbo 2.5, 6 on Multilingual v2 and 7 on Dialogue v3. You see the exact price on the Generate button before you click, and you are only charged when the audio is ready.
66 voices — narrators, conversational, announcers, characters — each with a preview you can play before generating. The models speak 30+ languages including English, Spanish, French, German, Japanese, Chinese, Hindi and Arabic, and detect the language automatically.
Turbo 2.5 is fast and the cheapest, good for most scripts. Multilingual v2 sounds the most natural over long narration and audiobooks. Dialogue v3 does multi-speaker conversations and understands emotion tags like [laughs], [whispers] or [sighs].
Up to 5,000 characters per generation — roughly five minutes of speech. For a longer script, split it into chapters.
Yes. On the Voice Cloning page you read a short passage aloud (about 30 seconds) and your voice is ready in a minute — free to create. You can only clone your own voice.
An MP3 you can play in the browser and download. It works in any video editor, podcast tool or e-learning platform.
Commercial usage rights are included on every paid plan — YouTube, ads, podcasts, courses, apps. You are responsible for the text you submit.
18 credits on sign-up, no card. 60+ voices, 30+ languages, multi-speaker dialogue.