Sam Audio

Audio separation with SAM Audio. Isolate any sound using natural language—professional-grade audio editing made simple for creators, researchers, and accessibility applications.

Inference$ Commercial useFrom 2 credits per run

About Sam Audio

Audio separation with SAM Audio. Isolate any sound using natural language—professional-grade audio editing made simple for creators, researchers, and accessibility applications.

audio-to-audiosam-audio

Pricing

A run with the default settings costs 2 credits. The exact cost updates in the playground as you change settings, and you're only charged when you press Run. Failed runs are refunded automatically.

Inputs

audio_urlfilerequired

URL of the audio file to process.

prompttextarea

Text prompt describing the sound to isolate. Optional but recommended - helps the model identify what type of sound to extract from the span.

spansjsonrequired

Time spans where the target sound occurs which should be isolated.

reranking_candidatesintegerdefault: 1

Number of candidates to generate and rank. Higher improves quality but increases latency and cost. Requires text prompt; ignored for span-only separation.

accelerationselectdefault: "balanced"

The acceleration level to use.

Options: fast, balanced, quality

max_chunk_durationnumberdefault: 60

Maximum audio duration (in seconds) to process in a single pass. Longer audio will be chunked with overlap and blended.

chunk_overlapnumberdefault: 5

Overlap duration (in seconds) between chunks for crossfade blending.

use_sound_activity_rankingbooleandefault: false

Use sound activity detection to rank reranking candidates based on how well each candidate's non-silent regions match the provided spans. Enables effective reranking even without a text prompt (span-only separation). Requires reranking_candidates > 1.

trim_to_spanbooleandefault: false

Trim output audio to only include the specified span time range. If False, returns the full audio length with the target sound isolated throughout.

output_formatselectdefault: "wav"

Output audio format.

Options: wav, mp3

More from Sam Audio

Sam Audio

Audio separation with SAM Audio. Isolate any sound using natural language—professional-grade audio editing made simple for creators, researchers, and accessibility applications.

sam-audio

audio-to-audio

Sam Audio

Audio separation with SAM Audio. Isolate any sound using natural language—professional-grade audio editing made simple for creators, researchers, and accessibility applications.

sam-audio

video-to-audio

Related audio to audio models

Demucs

SOTA stemming model for voice, drums, bass, guitar and more.

audio

audio-to-audio

ElevenLabs Audio Isolation

Isolate audio tracks using ElevenLabs advanced audio isolation technology.

audio

audio-to-audio

Audio Understanding

A audio understanding model to analyze audio content and answer questions about what's happening in the audio based on user prompts.

utilityaudio

audio-to-audio

ElevenLabs Voice Changer

Change the voices in your audios with voices in ElevenLabs!

voice-change

audio-to-audio

Qwen 3 TTS - Clone Voice [1.7B]

Clone your voices using Qwen3-TTS Clone-Voice model with zero shot cloning capabilities and use it on text-to-speech models to create speeches of yours!

clone-voicevoice-clone

audio-to-audio

Kling Video Create Voice

Create Voices to be used with Kling Models Voice Control

audio-to-audio

FFmpeg API [Merge Audios]

Merge audios into a single audio using FFmpeg API!

ffmpeg

audio-to-audio

VEED Clean Audio

Studio-quality speech from noisy recordings

speech enhancementnoise reduction

audio-to-audio

ACE Step Audio To Audio

Generate music from a lyrics and example audio using ACE-Step

audio-edit

audio-to-audio

DeepFilterNet 3

Enhance speech audio by removing background noise and upsampling to 48KHz

speech-enhancement

audio-to-audio

Stable Audio 3 Medium Audio to Audio

Stable Audio 3 Medium audio-to-audio is a 1.4 billion parameter latent diffusion model that transforms an input audio clip into new stereo variations up to 6 minutes guided by a text prompt.

musicstyle-transfer

audio-to-audio

Stable Audio 2.5

Generate high quality music and sound effects using Stable Audio 2.5 from StabilityAI

audio

audio-to-audio