Credited skills
11 skills · 35 min
Skills
Skill 10 of 11
Remove background noise and isolate vocals/speech from audio using ElevenLabs Voice Isolator (audio isolation) API.
1 minute · 203 words · 12 sections
Install
npx skills add elevenlabs/skills --skill voice-isolatornpx skills add elevenlabs/skillsThe first command installs just this skill, by the name in its SKILL.md; the second installs the whole repository.
Removes background noise from audio and isolates vocals/speech — useful for cleaning up noisy recordings, prepping audio for transcription, or pulling dialogue out of a mixed track.
Setup: See Installation Guide (opens in a new tab). For JavaScript, use
@elevenlabs/*packages only.
from elevenlabs import ElevenLabs
client = ElevenLabs()
with open("noisy.mp3", "rb") as audio_file:
audio_stream = client.audio_isolation.convert(audio=audio_file)
with open("clean.mp3", "wb") as f:
for chunk in
import { ElevenLabsClient } from "@elevenlabs/elevenlabs-js";
import { createReadStream, createWriteStream } from "fs";
const client = new ElevenLabsClient();
const audioStream = await client.audioIsolation.convert({
audio: createReadStream("noisy.mp3"),
});
audioStream.pipe(elevenlabs audio-isolation convert --audio noisy.mp3 --output clean.mp3| Parameter | Type | Default | Description |
|---|---|---|---|
audio | file (required) | — | Audio file with vocals/speech to isolate |
file_format | string | other | other for any encoded audio, or pcm_s16le_16 for 16-bit PCM mono @ 16kHz little-endian (lower latency) |
import requests
from io import BytesIO
from elevenlabs import ElevenLabs
client = ElevenLabs()
audio_url = "https://example.com/noisy.mp3"
response = requests.get(audio_url)
audio_data = BytesIO(response.content)
audio_stream = client.audio_isolation.convert(audio=audio_data)
with
If you already have raw 16-bit PCM mono @ 16kHz, passing file_format="pcm_s16le_16" skips decoding and reduces latency:
audio_stream = client.audio_isolation.convert(
audio=pcm_bytes,
file_format="pcm_s16le_16",
)Any common encoded audio/video container works as input (MP3, WAV, M4A, FLAC, OGG, WebM, MP4, etc.). Response is a streamed MP3 by default.
speech_to_text.convert() for better transcription accuracy.try:
audio_stream = client.audio_isolation.convert(audio=audio_file)
except Exception as e:
print(f"Voice isolation failed: {e}")Common errors:
file_format for the supplied audio)Remove background noise and isolate vocals/speech from audio using ElevenLabs Voice Isolator (audio isolation) API. Use when cleaning up noisy recordings, removing music or background ambience from dialogue, isolating speech from field recordings, preparing audio for transcription, extracting vocals, or any "denoise / clean up / isolate voice" task.
The verbatim description from this skill’s front matter — the string an agent matches on to decide whether to load it.
voice-isolator/SKILL.mdmain, last pushed 16 September 2026.SKILL.md, not by matching a directory convention. 2 distinct layouts observed: .agents/skills/*/SKILL.md, */SKILL.md.h1 and no skipped levels:/elevenlabs/skills.md, and each skill at its own .md URL.1 file · 2 KB
Everything this skill ships beside its prose. All of it is set here, as a subchapter of skill 10.
Documentation the agent loads on demand, rather than up front.