Turn scripted dialogue into natural multi-voice audio.
The ElevenLabs Text-to-Dialogue v3 API converts a sequence of dialogue turns — each with its own voice — into a single expressive audio file. Built for conversations, it captures emotion, pacing, and turn-taking across 70+ languages.
Model capabilities
Use ElevenLabs Text-to-Dialogue v3 from the same platform surface as the rest of your video and image stack: API keys, credits, logs, webhooks, and docs stay consistent across providers.
Assign a distinct ElevenLabs voice to each dialogue turn for believable multi-character conversations.
Eleven v3 captures emotion, emphasis, and natural turn-taking for lifelike back-and-forth dialogue.
Auto-detect or pin the language across 70+ supported languages, with consistent voices throughout.
Tune the stability parameter to balance consistency against expressive variation between generations.
Send a dialogue array of { text, voice } turns, optional stability and language_code, and a callback URL to the audio endpoint.
Use the returned task ID to poll status, or let the callback deliver completion and failure events.
Completed tasks return a mirrored audio URL through the same response shape used by other models.
AI Video APIcurl -X POST https://api.aivideoapi.ai/v1/audio/generations \
-H "Authorization: Bearer sk-your-api-key" \
-H "Content-Type: application/json" \
-d '{
"model": "elevenlabs-text-to-dialogue-v3",
"input": {
"dialogue": [
{ "text": "Hey! Did you finish the report?", "voice": "21m00Tcm4TlvDq8ikWAM" },
{ "text": "Almost — just adding the final numbers.", "voice": "AZnzlk1XvdvUeBnXmlld" }
],
"stability": 0.5,
"language_code": "auto"
}
}'Frequently asked questions
It is a multi-speaker text-to-speech API powered by ElevenLabs Eleven v3, exposed through AI Video API. You provide an ordered list of dialogue turns, each with its own voice, and receive a single hosted audio file rendering the full conversation. Generation is asynchronous with callbacks or polling.
Pricing is per character, based on the combined length of all dialogue text in a request. Open the playground to see the exact per-character credit rate and a live cost estimate. Credits are pre-charged on submit and automatically refunded if generation fails.
A single request supports up to 10 distinct voices and a combined total of 5000 characters across all dialogue turns. Each turn specifies its own ElevenLabs voice ID or preset name.
Eleven v3 supports 70+ languages. Leave language_code as auto to auto-detect, or pin a specific code such as en, zh, ja, or fr.
Pricing and usage
Billed by total dialogue text length
Distinct voice IDs
Total across all turns
Create one API key, use one credit balance, and switch between video and image models without provider-specific plumbing.