ElevenLabs Text to Dialogue v3 API
ElevenLabs v3 voices full conversations between several speakers, with interruptions, laughs and whispers directed from the script.
Prices are temporarily unavailable — refresh the page in a minute.
What ElevenLabs Text to Dialogue v3 is good for
ElevenLabs Text to Dialogue v3 takes a script with several speakers and returns one finished audio conversation, with natural timing, turn-taking and even interruptions, so there are no separate voice tracks to stitch together. Inline tags such as [whispers], [laughs] or [sarcastic] direct the delivery line by line, in more than 70 languages. It suits podcasts, audio dramas, game scenes and explainers told as a conversation.
- Two-host podcast segments produced from a written script
- Audio dramas and bedtime stories with several characters
- Game cutscenes and character banter with reactions and interruptions
- Explainer videos told as a conversation instead of a lecture
- Practice dialogues for language-learning lessons in many languages
ElevenLabs Text to Dialogue v3 pricing
| Option | Price, USD | Video Blade tokens |
|---|---|---|
| Text to dialogue | tokens |
Prices are per 1,000 characters (about a minute of speech) and live from our price list. Tokens are held when a run starts and settled to what was actually used; a failed run costs nothing.
ElevenLabs Text to Dialogue v3 is coming soon to Video Blade
It is listed with its live price so you can compare it. You can't order it through Video Blade yet.
ElevenLabs Text to Dialogue v3 FAQ
How much does ElevenLabs Text to Dialogue v3 cost?
1,000 characters from . Prices are live from our price list, and you see the exact price before anything runs.
How do audio tags work in ElevenLabs v3 dialogue?
You write short cues in square brackets inside a line, such as [whispers], [laughs], [sighs] or [excited], and the voice acts them out instead of reading them aloud. Tags work best at key emotional moments; packing them into every sentence tends to make the conversation sound overacted and less consistent.
Why do ElevenLabs v3 results vary from take to take?
Eleven v3 still carries an alpha label, so the same script can come out somewhat differently each time. Clear structure helps: deliberate punctuation, ellipses for pauses, tags only where they matter, and long scripts split into scenes or speaker turns. Expect some experimenting before the output feels consistent.
Can I use ElevenLabs Text to Dialogue v3 on Video Blade today?
Not yet. ElevenLabs Text to Dialogue v3 is listed with its live price so you can compare it with the models you can use today; ordering it through Video Blade is coming soon.
How is ElevenLabs Text to Dialogue v3 billed?
Per 1,000 characters of the text you send to be spoken. Tokens are held when a run starts and settled to what was actually used; a failed run costs nothing. Current prices are shown on this page.
ElevenLabs Text to Dialogue v3 in the Video Blade API
elevenlabs-text-to-dialogue-v3Ordering this model through the API is coming soon.