Use Eleven V3 with Comfy Router

Call elevenlabs/eleven_v3 through Comfy Router: endpoint, request shape and the response Router returns.

API Reference for elevenlabs/eleven_v3, served by Comfy Router from Elevenlabs.

Quick start

Create a key at platform.comfy.org/profile/api-keys and export it as COMFY_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

Python

from comfy_sdk import Comfy

# Reads COMFY_API_KEY from the environment. Each call sends a fresh
# Idempotency-Key and waits up to 10 minutes for the finished result.
with Comfy() as client:
    result = client.models.run(
        "elevenlabs/eleven_v3",
        {
            "inputs": [
                {
                    "text": "Hello from Comfy Router.",
                    "voice_id": "21m00Tcm4TlvDq8ikWAM",
                },
            ],
        },
    )

print(result)

Schema

Input

apply_text_normalization · 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 skipped

Possible values: auto, on, off

inputs · object[] · 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.

inputs[].text · string · required

The text to be converted into speech.

inputs[].voice_id · string · required

The ID of the voice to be used for the generation.

language_code · 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.

model_id · 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.

pronunciation_dictionary_locators · 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.

pronunciation_dictionary_locators[].pronunciation_dictionary_id · string · required

The ID of the pronunciation dictionary

pronunciation_dictionary_locators[].version_id · string · required

The version ID of the pronunciation dictionary

seed · 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 4294967295

settings · object

Settings controlling the dialogue generation

settings.stability · 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: double

Generated from the schema Router serves at GET /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

{
  "inputs": [
    {
      "text": "Hello from Comfy Router.",
      "voice_id": "21m00Tcm4TlvDq8ikWAM"
    }
  ]
}

Before you ship

The snippets above are the shortest working call. Three things are the same for every model and are documented once on the Comfy Router headers page: send an Idempotency-Key on every paid call and reuse it when you retry, expect the connection to be held up to Router’s 10 minute deadline, and keep X-Comfy-Request-Id from every response. The SDKs do all three for you; the cURL tab does none of them. On failure, X-Comfy-Error-Type names the bucket, and a 422 means the body failed the model’s schema and was never billed.

Headers

Authentication, idempotency, request IDs, error buckets, retry pacing, spend limits.

Quick Start

Typed error handling in Python and TypeScript, reading the 422, walking the catalog.

Limitations

What Router does not do today, and what to use instead.