
Output
audio
LLM-ready
API & LLM schema
Exact request contract for this model. Agents can fetch it from /api/v1/models?id=elevenlabs/text-to-dialogue/eleven-v4.
POST
/api/v1/generate16 fields · 2 required| Field | Type | Requirement | Contract |
|---|---|---|---|
model_id | constant | Required | ArtEmotion model identifier. |
extra | object | Optional | Model-specific settings may also be nested here. |
max_credits | number | Optional | Reject before submission if the estimated list price exceeds this cap. · Range: 1–… |
webhook_url | string | Optional | Format: uri |
webhook_secret | string | Optional | Optional model input. |
folder_id | string | Optional | Optional model input. |
inputs | array<object> | Required | Dialogue turns using premade voice names. Maximum 10 different voices and 2,000 total text characters per job. · Items: 1–100 |
stability | number | Optional | Default: 0.5 · Range: 0–1 |
similarity | number | Optional | Default: 0.75 · Range: 0–1 |
language_code | string | Optional | Optional two-letter ISO code (en, es, fr…). Leave empty for automatic detection; over 90 languages supported. |
apply_text_normalization | string | Optional | Allowed: auto, on, off · Default: auto |
seed | integer | Optional | -1 for random; reproducibility is best effort. · Range: -1–4294967295 |
output_format | string | Optional | Allowed: mp3_44100_128 · Default: mp3_44100_128 |
previous_text | string | Optional | Optional preceding text for delivery continuity, not spoken. Up to 100 characters; support depends on the model. |
future_text | string | Optional | Optional following text for delivery continuity, not spoken. Up to 100 characters; support depends on the model. |
pronunciation_dictionary_locators | array<object> | Optional | Items: 0–3 |
Minimal request example
{
"model_id": "elevenlabs/text-to-dialogue/eleven-v4",
"inputs": []
}Raw JSON Schema
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://www.artemotion.ai/api/v1/models?id=elevenlabs%2Ftext-to-dialogue%2Feleven-v4",
"title": "ElevenLabs v4 Dialogue generation request",
"description": "Request body accepted by POST /api/v1/generate for elevenlabs/text-to-dialogue/eleven-v4.",
"type": "object",
"properties": {
"model_id": {
"type": "string",
"const": "elevenlabs/text-to-dialogue/eleven-v4",
"description": "ArtEmotion model identifier."
},
"extra": {
"type": "object",
"additionalProperties": true,
"description": "Model-specific settings may also be nested here."
},
"max_credits": {
"type": "number",
"minimum": 1,
"description": "Reject before submission if the estimated list price exceeds this cap."
},
"webhook_url": {
"type": "string",
"format": "uri",
"maxLength": 2048
},
"webhook_secret": {
"type": "string",
"maxLength": 512
},
"folder_id": {
"type": "string"
},
"inputs": {
"type": "array",
"minItems": 1,
"maxItems": 100,
"description": "Dialogue turns using premade voice names. Maximum 10 different voices and 2,000 total text characters per job.",
"items": {
"type": "object",
"additionalProperties": false,
"required": [
"voice",
"text"
],
"properties": {
"voice": {
"type": "string",
"description": "Premade voice name, for example Rachel or Sarah. Raw provider IDs and cloned voices are not supported in dialogue."
},
"text": {
"type": "string",
"minLength": 1,
"maxLength": 2000
}
}
}
},
"stability": {
"title": "Stability",
"default": 0.5,
"type": "number",
"minimum": 0,
"maximum": 1,
"multipleOf": 0.05
},
"similarity": {
"title": "Voice similarity",
"default": 0.75,
"type": "number",
"minimum": 0,
"maximum": 1,
"multipleOf": 0.05
},
"language_code": {
"title": "Language code",
"description": "Optional two-letter ISO code (en, es, fr…). Leave empty for automatic detection; over 90 languages supported.",
"type": "string",
"maxLength": 2
},
"apply_text_normalization": {
"title": "Text normalization",
"default": "auto",
"type": "string",
"enum": [
"auto",
"on",
"off"
]
},
"seed": {
"title": "Seed",
"description": "-1 for random; reproducibility is best effort.",
"type": "integer",
"minimum": -1,
"maximum": 4294967295
},
"output_format": {
"title": "Output format",
"default": "mp3_44100_128",
"type": "string",
"enum": [
"mp3_44100_128"
]
},
"previous_text": {
"title": "Previous context",
"description": "Optional preceding text for delivery continuity, not spoken. Up to 100 characters; support depends on the model.",
"type": "string",
"maxLength": 100
},
"future_text": {
"title": "Following context",
"description": "Optional following text for delivery continuity, not spoken. Up to 100 characters; support depends on the model.",
"type": "string",
"maxLength": 100
},
"pronunciation_dictionary_locators": {
"type": "array",
"maxItems": 3,
"items": {
"type": "object",
"additionalProperties": false,
"required": [
"pronunciation_dictionary_id"
],
"properties": {
"pronunciation_dictionary_id": {
"type": "string",
"minLength": 1
},
"version_id": {
"type": "string",
"minLength": 1
}
}
}
}
},
"required": [
"model_id",
"inputs"
],
"additionalProperties": false
}FAQ
How much does ElevenLabs v4 Dialogue cost on ArtEmotion?
Credit-based pricing. You pay in ArtEmotion credits — every plan and top-up converts USD to credits at a fixed rate.
Do I get my credits back if ElevenLabs v4 Dialogue fails?
Yes — failed generations are never charged. The credits are released back to your balance automatically.
Can I call ElevenLabs v4 Dialogue from the API?
Yes. Use POST /api/v1/generate with model_id: "elevenlabs/text-to-dialogue/eleven-v4". See the API reference for the full schema.
Where are my generations stored?
Every output is saved to your personal Library. You can export or delete everything any time from Privacy & deletion.
Ready to generate with ElevenLabs v4 Dialogue?
Start now →No commitment. New accounts get 50 free credits on signup. See pricing.