Tell it how to say it.
IllustrationTags like [whispers] and [laughs] change the performance where you put them. A voiceover you direct, not one you accept.
Ad voiceovers
Energy where the hook needs it, calm where the offer lands.
Character voices
Performances for animation and storytelling.
Faceless narration
A voice with personality for channels without a presenter.
Avatar scripts
The voice behind a Kling Avatar 2 talking video.
- Provider
- ElevenLabs
- Voices
- 21 stock voices
- Languages
- 29, or automatic detection
- Direction
- Audio tags like [whispers], [laughs], [excited]
- Delivery
- Creative, Natural or Steady
- Plans
- Hobby and up
- Cost
- 17 credits per 1,000 characters
What is ElevenLabs v3?
ElevenLabs v3 is ElevenLabs' most expressive text to speech model. It reads a script in one of 21 voices across 29 languages, and responds to audio tags written into the text, such as [whispers], [laughs] and [excited], so the delivery can be directed line by line. A delivery setting runs from Creative, the most expressive and most responsive to tags, through Natural to Steady. On APImage it costs 17 credits per 1,000 characters, in the same Audio studio as music, sound effects and dubbing.
How much does ElevenLabs v3 cost on APImage?
17 credits per 1,000 characters of script.
What are audio tags?
Bracketed directions in the script, such as [whispers], [laughs] or [excited], that change how the next words are performed. They work best with Creative delivery.
How many languages does it speak?
29, with automatic detection or a language you set.
Which plan includes it?
Hobby and up.
How do I use it?
Open the Audio studio, choose Text to speech and pick ElevenLabs v3. Pick a voice and a delivery setting. Write the script, with tags like [whispers] where you want them. Generate.