ElevenLabs audio-isolation 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
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
ÜBERBLICK
ElevenLabs audio-isolation is available through the same RunAPI auth, SDKs, and agent skill workflow.
- Unified endpoint
- SDK snippets
- Agent install path
- Fehlgeschlagene Generierungen werden nicht berechnet
PREISE
PREISE
Fehlgeschlagene Generierungen werden nicht berechnet
Isolate audio
$0.12
/ minute
DATENBLATT
DATENBLATT
| Model ID | audio-isolation |
| Anbieter | ElevenLabs |
| Modalität | audio_music |
| Task type | asynchronous |
| Abrechnung | minute |
| Endpoint | /api/v1/elevenlabs/isolate_audio |
| Commercial | Yes |
| Status | Operational |
QUICKSTART
Quickstart — audio-isolation
curl -X POST https://runapi.ai/api/v1/elevenlabs/isolate_audio \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "audio-isolation",
"audio_url": "https://cdn.runapi.ai/public/samples/voice.mp3"
}'
import { ElevenlabsClient } from "@runapi.ai/elevenlabs";
const client = new ElevenlabsClient();
const result = await client.isolateAudio.run({
model: "audio-isolation",
audio_url: "https://cdn.runapi.ai/public/samples/voice.mp3",
});
require "runapi/elevenlabs"
client = RunApi::Elevenlabs::Client.new
result = client.isolate_audio.run(
model: "audio-isolation",
audio_url: "https://cdn.runapi.ai/public/samples/voice.mp3"
)
SO FUNKTIONIERT ES
How to use audio-isolation
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.
UNTERSCHIEDE
How audio-isolation compares
VS SOUND-EFFECT-V2
Vocal extraction from mixed audio sources
Text-to-sound effects for games, video, and podcasts
VS SPEECH-TO-TEXT
Vocal extraction from mixed audio sources
Transcription across 29+ languages with speaker diarization
VS TEXT-TO-DIALOGUE-V3
Vocal extraction from mixed audio sources
Multi-speaker dialogue generation with natural turn-taking
ANWENDUNGSFÄLLE
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 audio-isolation
How do I select audio-isolation?
Pass the model ID shown in the quickstart.
Is pricing usage-based?
Yes. Pricing is metered per call or unit.
Other ElevenLabs variants
speech-to-text
Cheapest
speech-to-text
$0.040 / minute
text-to-speech-turbo-v2.5
Fast
text-to-speech-turbo-v2.5
$0.060 / 1K chars
text-to-speech-multilingual-v2
text-to-speech-multilingual-v2
$0.120 / 1K chars
text-to-dialogue-v3
text-to-dialogue-v3
$0.140 / 1K chars
sound-effect-v2
sound-effect-v2
$0.150 / minute
Related models
JETZT STARTEN