Use Eleven Sfx V2 with Comfy Router

Call elevenlabs/eleven_sfx_v2 through Comfy Router: endpoint, request shape and the response Router returns.

API Reference for elevenlabs/eleven_sfx_v2, served by Comfy Router from Elevenlabs.

Quick start

Create a key in your Comfy workspace 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_sfx_v2

Endpoint: POST https://api.comfy.org/v2/models/elevenlabs/eleven_sfx_v2

Wait for the result

Python

from comfy_sdk import Comfy

# Reads COMFY_API_KEY from the environment.
# The SDK automatically creates an idempotency key and reuses it for automatic retries.
with Comfy() as client:
    result = client.models.run(
        "elevenlabs/eleven_sfx_v2",
        {
            "duration_seconds": 5,
            "text": "A distant rumble of thunder rolling across a valley.",
        },
    )

print(result)

Queue and collect later

Queued delivery is rolling out per workspace. Until yours is enabled, the submit route answers 403 with X-Comfy-Error-Type: not_enabled. Nothing about the request is wrong, and the same body works through the synchronous route in the meantime.

The same body, sent to POST https://api.comfy.org/v2/models/elevenlabs/eleven_sfx_v2/requests. Router answers 201 with a request_id as soon as the run is admitted, and the result is collected once it is ready, from this process or another one. Queued delivery walks through status, cancellation and collection.

Python

from comfy_sdk import Comfy

# Reads COMFY_API_KEY from the environment.
# Each submit() call mints its own Idempotency-Key and reuses it for automatic retries.
with Comfy() as client:
    handle = client.models.submit(
        "elevenlabs/eleven_sfx_v2",
        {
            "duration_seconds": 5,
            "text": "A distant rumble of thunder rolling across a valley.",
        },
    )
    print("request_id:", handle.request_id)  # with the model ID, all another process needs

    # Poll until the request completes, waiting the Retry-After the server names.
    for update in handle.iter_events():
        print(update.status, update.queue_position)

    # The provider's own payload, the same value models.run() returns.
    # A request that failed or was cancelled raises the typed Router error here.
    result = handle.get()

print(result)

Schema

Input

duration_seconds · number · required

The duration of the sound which will be generated in seconds. Must be at least 0.5 and at most 30. REQUIRED on this route: unlike the upstream ElevenLabs API, which guesses an optimal duration when the field is null, this route rejects a request that omits it with 400 “Duration is required”. The field stays nullable only so an explicit null is a well-formed document; it is still refused. This value is the quantity the request is metered on.

Range: 0.5 to 30

Format: double

loop · boolean · default: "false"

Whether to create a sound effect that loops smoothly. ElevenLabs documents this as available only for the ‘eleven_text_to_sound_v2’ model, which is the model this route forwards ‘eleven_sfx_v2’ as (see model_id), so it applies here.

model_id · string

The model ID to use for the sound generation. This route admits ‘eleven_sfx_v2’ and nothing else; any other value is rejected with 400 before the request reaches ElevenLabs. ‘eleven_sfx_v2’ is Comfy’s id for the model ElevenLabs calls ‘eleven_text_to_sound_v2’; the proxy rewrites the forwarded body to that vendor spelling, which ElevenLabs’ own enum requires (it refuses ‘eleven_sfx_v2’ with 422), so a caller never sends the vendor id. 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.

prompt_influence · number

A higher prompt influence makes your generation follow the prompt more closely while also making generations less variable. Must be a value between 0 and 1. Defaults to 0.3.

Range: 0 to 1

Format: double

text · string · required

The text that will get converted into a sound effect.

Generated from the schema Router serves at GET /v2/models/elevenlabs/eleven_sfx_v2/openapi.json, the same document it validates a call against before the request reaches the provider.

Output

*/* · string (binary)

Raw audio bytes. The Content-Type and encoding follow the requested output_format and are forwarded from ElevenLabs. The example is a placeholder for the binary body, not JSON or base64.

Examples

Input

{
  "duration_seconds": 5,
  "text": "A distant rumble of thunder rolling across a valley."
}

Output

Binary body: raw bytes rather than a JSON document, returned as */*, so there is no JSON example to show. The response Content-Type and encoding follow the request, as the Output schema above describes.

Before you ship

The SDKs create an Idempotency-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.