バリアント · ElevenLabs / ElevenLabs

ElevenLabs sound-effect-v2 API

A model variant exposed through RunAPI's unified AI API.

Operational · audio_music · Commercial use supported
# Works with Claude Code, Codex, Gemini CLI, Cursor, and 50+ agents
npx skills add runapi-ai/elevenlabs -g
The -g flag installs globally so every project picks it up.
Or paste this prompt to your AI agent:
Install the ElevenLabs skill for me:

1. Clone https://github.com/runapi-ai/elevenlabs
2. Copy the skills/elevenlabs/ directory into your
   user-level skills directory (e.g. ~/.claude/skills/
   for Claude Code, ~/.codex/skills/ for Codex).
3. Verify that SKILL.md is present.
4. Confirm the install path when done.
Switch variant
概要

ElevenLabs sound-effect-v2 is available through the same RunAPI auth, SDKs, and agent skill workflow.

  • Unified endpoint
  • SDK snippets
  • Agent install path
  • 失敗した生成は課金されません
料金

料金

失敗した生成は課金されません
Text to sound
$0.15 / minute
仕様

仕様

Model ID sound-effect-v2
プロバイダー ElevenLabs
モダリティ audio_music
Task type asynchronous
課金 minute
Endpoint /api/v1/elevenlabs/text_to_sound
Commercial Yes
Status Operational
クイックスタート

Quickstart — sound-effect-v2

runapi.ai
curl -X POST https://runapi.ai/api/v1/elevenlabs/text_to_sound \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "sound-effect-v2",
  "text": "Convert this paragraph into natural speech with a warm British male voice, moderate pace."
}'
import { ElevenlabsClient } from "@runapi.ai/elevenlabs";

const client = new ElevenlabsClient();
const result = await client.textToSound.run({
    model: "sound-effect-v2",
    text: "Convert this paragraph into natural speech with a warm British male voice, moderate pace.",
});
require "runapi/elevenlabs"

client = RunApi::Elevenlabs::Client.new
result = client.text_to_sound.run(
    model: "sound-effect-v2",
    text: "Convert this paragraph into natural speech with a warm British male voice, moderate pace."
)
@runapi.ai/elevenlabs v1
仕組み

How to use sound-effect-v2

01

Choose endpoint

Pick the endpoint and copy the SDK snippet.

02

Pass model ID

Use this variant ID in the request body.

03

Run task

Submit the request and store the returned task ID.

04

Collect output

Poll or receive the callback when the task finishes.

違い

How sound-effect-v2 compares

VS AUDIO-ISOLATION

Text-to-sound effects for games, video, and podcasts

Vocal extraction from mixed audio sources

VS SPEECH-TO-TEXT

Text-to-sound effects for games, video, and podcasts

Transcription across 29+ languages with speaker diarization

VS TEXT-TO-DIALOGUE-V3

Text-to-sound effects for games, video, and podcasts

Multi-speaker dialogue generation with natural turn-taking

ユースケース

Where to use this variant

Music generation

Create tracks and audio assets.

Voice workflows

Build speech and audio pipelines.

Agent creation

Expose audio tools to agents.

FAQ

Frequently asked questions about sound-effect-v2

How do I select sound-effect-v2?

Pass the model ID shown in the quickstart.

Is pricing usage-based?

Yes. Pricing is metered per call or unit.

今すぐ開始

Start with ElevenLabs today.