elevenlabs/eleven_v3, served by Comfy Router from Elevenlabs.
Quick start
Create a key at platform.comfy.org/profile/api-keys and export it asCOMFY_API_KEY. The Python and TypeScript snippets use the Comfy SDKs (pip install comfy-sdk, npm install @comfyorg/sdk); the cURL snippet is the same call over raw HTTP.
Model ID: elevenlabs/eleven_v3
Endpoint: POST https://api.comfy.org/v2/models/elevenlabs/eleven_v3
Schema
Input
string
default:"\"auto\""
Controls text normalization with three modes:
‘auto’ - system automatically decides whether to apply text normalization
‘on’ - text normalization will always be applied
‘off’ - text normalization will be skippedPossible values:
auto, on, offobject[]
required
A list of dialogue inputs, each containing text and a voice ID which will be converted into speech.
The maximum number of unique voice IDs is 10.
string
required
The text to be converted into speech.
string
required
The ID of the voice to be used for the generation.
string
Language code (ISO 639-1) used to enforce a language for the model and text normalization.
If the model does not support provided language code, an error will be returned.
string
Identifier of the model that will be used. This route admits
‘eleven_v3’ and nothing else; any other value is rejected with 400
before the request reaches ElevenLabs.
The upstream ElevenLabs advice to query GET /v1/models for the
available set does NOT describe this route, which serves one model.
It is NOT in this schema’s
required list because Comfy Router
fills it from the {model} path segment of
/v2/models/elevenlabs/{model}, so a Router caller omits it.object[]
A list of pronunciation dictionary locators (id, version_id) to be applied to the text.
They will be applied in order. You may have up to 3 locators per request.
string
required
The ID of the pronunciation dictionary
string
required
The version ID of the pronunciation dictionary
integer
If specified, our system will make a best effort to sample deterministically.
Repeated requests with the same seed and parameters should return the same result.
Must be integer between 0 and 4294967295.Range:
0 to 4294967295object
Settings controlling the dialogue generation
number
default:"0.5"
Determines how stable the voice is and the randomness between each generation.
Lower values introduce broader emotional range for the voice.
Higher values can result in a monotonous voice with limited emotion.Format:
doubleGET /v2/models/elevenlabs/eleven_v3/openapi.json, the same document it validates a call against before the request reaches the provider.
Output
Router does not publish an output schema for this model.Examples
Input
Before you ship
The SDKs create anIdempotency-Key and reuse it for automatic retries. For manual retries, reuse the original key. Router can hold the connection for up to 10 minutes.
When a request fails, Router sends an X-Comfy-Error-Type response header explaining why. A 422 means Router rejected the input before calling the provider. Download generated assets promptly because result URLs can expire.
Headers
Authentication, idempotency, request IDs, error buckets, retry pacing, spend limits.
Using the Router API
Model discovery, validation errors, retries, and billing.
Limitations
What Router does not do today, and what to use instead.