ElevenLabs Text-to-Dialogue v3 / v4

Generate natural, expressive multi-speaker dialogue audio with ElevenLabs Eleven v3 or v4. Provide a sequence of dialogue turns, each with its own voice, and receive a single hosted audio file. Supports multiple languages.

Models

ModelStabilityOutput
elevenlabs-text-to-dialogue-v30, 0.5, or 1; default 0.5MP3
elevenlabs-text-to-dialogue-v4Any number from 0 to 1; default 0.5MP3

Try v3 in the Playground or v4 in the Playground. Both models use the same request and task response format.

Generation uses the official Text-to-Dialogue API. See the Eleven v4 overview for the newer model's capabilities.

Pricing

Both models cost 24 credits per 1,000 Unicode characters, with no minimum charge. Sum all dialogue[].text characters, including spaces and audio tags, then round the request price to two decimal places. A supplementary Unicode character such as an emoji counts as one character.

CharactersBase credits
10.02
1002.40
1,00024.00
2,00048.00

Your account pricing multiplier applies after the base price is rounded. The estimate endpoint returns your final charge before submission. Credits are pre-charged on submit and refunded for failed generation; completed tasks are not refunded.

Each request supports up to 2,000 total Unicode characters and 10 distinct voice IDs. Input validation happens before charging.

Create Task

curl -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",
    "callback_url": "https://your-server.com/webhook",
    "input": {
      "dialogue": [
        { "text": "Hey! Did you finish the report?", "voice": "TX3LPaxmHKxFdv7VOQHJ" },
        { "text": "Almost — just adding the final numbers now.", "voice": "nPczCjzI2devNBz1zQrb" }
      ],
      "stability": 0.5,
      "language_code": "en"
    }
  }'

Request Body

FieldTypeRequiredDescription
modelstringYeselevenlabs-text-to-dialogue-v3 or elevenlabs-text-to-dialogue-v4
inputobjectYesGeneration parameters, see below
callback_urlstringNoURL to receive task completion/failure notifications

Input object

FieldTypeRequiredDescription
dialoguearrayYesNon-empty ordered list of { text, voice } turns; at most 2,000 Unicode characters in total and 10 distinct voices
dialogue[].textstringYesNon-empty spoken text; audio tags and whitespace count toward the character total
dialogue[].voicestringYesVoice ID; copy an ID from the verified catalog below
stabilitynumberNov3: 0, 0.5, or 1; v4: any number from 0 to 1. Default: 0.5
language_codestringNoOptional language code such as en, zh, ja, or fr; omit or leave blank for automatic detection

The output is a hosted MP3 audio file. Streaming and alternate output formats are not exposed by this endpoint.

Verified voices

The catalog contains verified voices, including official default voices, that are available to the official account. Other custom voices in the account are not automatically published. Names are display labels: always submit the voice ID. Voices can become unavailable; refresh the catalog before selecting a replacement.

NameStylevoice_idPreview
Liam - Energetic, Social Media CreatorA young adult with energy and warmth - suitable for reels and shorts.TX3LPaxmHKxFdv7VOQHJ
Callum - Husky TricksterDeceptively gravelly, yet unsettling edge.N2lVS1w4EtoT3dr4eOWO
Laura - Enthusiast, Quirky AttitudeThis young adult female voice delivers sunny enthusiasm with a quirky attitude.FGY2WhTYpPnrIDTdsKH5
Bella - Professional, Bright, WarmThis voice is warm, bright, and professional, characterized by a Standard American accent and a polished, narrative quality. It features a medium-high pitch with crisp diction and a deliberate, rhythmic pace that makes it highly intelligible and engaging for long-form listening.hpp4J3VqNfWAUOO0d1Us
Brian - Deep, Resonant and ComfortingMiddle-aged man with a resonant and comforting tone. Great for narrations and advertisements.nPczCjzI2devNBz1zQrb
Roger - Laid-Back, Casual, ResonantEasy going and perfect for casual conversations.CwhRBWXzGAHq8TQ4Fs17
Sarah - Mature, Reassuring, ConfidentYoung adult woman with a confident and warm, mature quality and a reassuring, professional tone.EXAVITQu4vr4xnSDxMaL
Charlie - Deep, Confident, EnergeticA young Australian male with a confident and energetic voice.IKne3meq5aSn9XLyUdCD
George - Warm, Captivating StorytellerWarm resonance that instantly captivates listeners.JBFqnCBsd6RMkjVDRZzb
River - Relaxed, Neutral, InformativeA relaxed, neutral voice ready for narrations or conversational projects.SAz9YHcvj6GT2YYXdXww
Harry - Fierce WarriorAn animated warrior ready to charge forward.SOYHLrjzK2X1ezoPC6cr
Alice - Clear, Engaging EducatorClear and engaging, friendly woman with a British accent suitable for e-learning.Xb7hH8MSUJpSbSDYk0k2
Matilda - Knowledgable, ProfessionalA professional woman with a pleasing alto pitch. Suitable for many use cases.XrExE9yKIg1WjnnlVkGX
Will - Relaxed OptimistConversational and laid back.bIHbv24MWmeRgasZH58o
Jessica - Playful, Bright, WarmYoung and popular, this playful American female voice is perfect for trendy content.cgSgspJ2msm6clMCkdW9
Eric - Smooth, TrustworthyA smooth tenor pitch from a man in his 40s - perfect for agentic use cases.cjVigY5qzO86Huf0OWal
Chris - Charming, Down-to-EarthNatural and real, this down-to-earth voice is great across many use-cases.iP95p4xoKVk53GoZ742B
Daniel - Steady BroadcasterA strong voice perfect for delivering a professional broadcast or news story.onwK4e9ZLuTAKqWW03F9
Lily - Velvety ActressVelvety British female voice delivers news and narrations with warmth and clarity.pFZP5JQG7iQjIQuC4Bku
Adam - Dominant, FirmA bright tenor pitch that immediately cuts through. The delivery is brash and openly confident, speaking with unwavering certainty and a slightly aggressive self-assurance.pNInz6obpgDQGcFmaJgB
Bill - Wise, Mature, BalancedFriendly and comforting voice ready to narrate your stories.pqHfZKP75CvOlQylNhV4

Response

{
  "code": 200,
  "msg": "success",
  "data": {
    "taskId": "a1b2c3d4-e5f6-7890-abcd-ef1234567890"
  }
}

Estimate

Preview the credit cost without creating a task. The cost scales with the total character count of dialogue[].text.

curl -X POST https://api.aivideoapi.ai/v1/estimate \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "elevenlabs-text-to-dialogue-v3",
    "input": {
      "dialogue": [
        { "text": "Hello there!", "voice": "TX3LPaxmHKxFdv7VOQHJ" }
      ]
    }
  }'

Query Task

curl https://api.aivideoapi.ai/v1/tasks/{taskId} \
  -H "Authorization: Bearer sk-your-api-key"

Status transitions: pending -> processing -> completed or failed.

Completed

{
  "id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
  "status": "completed",
  "model": "elevenlabs-text-to-dialogue-v3",
  "created_at": 1775383908,
  "completed_at": 1775383956,
  "output": {
    "urls": [
      "https://file.aivideoapi.ai/audio/2026/06/23/dialogue.mp3"
    ],
    "metadata": {
      "model": "elevenlabs-text-to-dialogue-v3"
    }
  }
}

Audio URLs are valid for 24 hours.

Failed

{
  "id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
  "status": "failed",
  "model": "elevenlabs-text-to-dialogue-v3",
  "created_at": 1775383908,
  "error": {
    "code": "upstream_error",
    "message": "Generation failed"
  }
}

When a task fails, pre-charged credits are automatically refunded.

Callback

Pass callback_url when creating the task. The system will automatically send a POST request to your URL when the task completes or fails. The format matches the query task response.


Error Codes

When a request fails, the API returns a JSON error response:

{
  "error": {
    "code": "insufficient_credits",
    "message": "Your credit balance is too low. Please top up.",
    "type": "billing_error"
  }
}

Error Reference

HTTP StatusCodeTypeDescription
400invalid_requestinvalid_request_errorMissing or invalid parameters
401invalid_api_keyauthentication_errorAPI key is invalid, disabled, or deleted
402insufficient_creditsbilling_errorCredit balance too low, please top up
403ip_not_allowedpermission_errorRequest IP not in the key's allowlist
404model_not_foundinvalid_request_errorModel does not exist or is inactive
404task_not_foundinvalid_request_errorTask ID does not exist
429rate_limit_exceededrate_limit_errorToo many requests, please slow down
429spend_limit_exceededbilling_errorKey spend limit reached (hourly/daily/total)
500internal_errorapi_errorUnexpected server error
503upstream_errorupstream_errorUpstream AI provider returned an error

Common Scenarios

invalid_request (400)

Returned when required fields are missing or invalid.

{
  "error": {
    "code": "invalid_request",
    "message": "'model' is required.",
    "type": "invalid_request_error"
  }
}

insufficient_credits (402)

Your balance is too low. Check your balance with GET /v1/credits and top up in Dashboard > Billing.

invalid_api_key (401)

Possible causes:

  • The key does not start with sk-
  • The key has been disabled or deleted
  • The user account has been banned

upstream_error (503)

The upstream AI provider returned an error. This may happen when:

  • The input contains sensitive or prohibited content
  • The provider is temporarily unavailable
  • The request parameters are not supported by the provider

Credits are automatically refunded when a task fails due to upstream errors.