Natural voices in dozens of languages. 1,000 characters start at $0.10.
The model reads your text in a natural voice, with pauses, intonation and emotion. Use it for videos, podcasts, audiobooks and phone menus.
Eleven v4 by ElevenLabs sounds best, v4 Turbo and Flash are faster and half the price, and OmniVoice is the cheapest. You can also clone your own voice from a recording.
Punctuation controls pauses. Spell out numbers and abbreviations.
| Models | Eleven v4, v4 Turbo, v3, Multilingual v2, Flash v2.5, OmniVoice |
| Voice cloning | from a recording |
| Format | MP3 |
| 1,000 characters | Tokens | USD |
|---|---|---|
| OmniVoice | 3,000 tokens | ≈ $0.10 |
| Flash v2.5 | 5,000 tokens | ≈ $0.17 |
| Eleven v4 Turbo | 5,000 tokens | ≈ $0.17 |
| Eleven v4 | 10,000 tokens | ≈ $0.33 |
USD shown at the Basic rate: $5 = 150,000 tokens. Larger plans cut the token price by up to 40%. Tokens never expire, and there is no subscription.
Yes. Upload a recording of your voice and the model reads texts with it.
1,000 characters in Eleven v4 cost 10,000 tokens, which is ≈ $0.33.
No. You top up once and pay per generation. Tokens never expire.