Explore

Stem Separation from Your Own Code

Hit the TwoShot REST API with an admin bearer. Stem-separate any audio source URL, poll the job, download all four stems. Same infrastructure TwoShot uses internally.

If you're building something that processes audio at scale — a transcription pipeline, a karaoke app, a music-search product, a podcast editor — the stem separation endpoint is the same one TwoShot uses internally. You authenticate with an admin bearer, POST the audio URL plus the model ID, and get back a job you poll until it's done. Every stem lives on CDN-backed storage; downloads are pre-signed URLs you can hand straight to your user. The infrastructure handles concurrency, retries, and GPU scheduling; your code stays thin. The quality target is broadcast-usable: vocals clean enough to drop into a karaoke app without noticeable bleed, drums isolated sharply enough to sample, bass kept coherent even on tracks with layered 808s. We run the same model tier in the API as on the web app, so if the browser output works for your use case, the API output is identical. For most integrations, the integration shape is: receive audio from your user, POST to TwoShot, return download links for the stems after ~30 seconds. The library returns per-stem URLs for vocals, drums, bass, and 'other' — plus an instrumental-only pass if you request it. For high-volume operations (thousands of concurrent jobs), ping us before you ship so we can pre-warm capacity on your tenant.

Read the API docs
play_arrow3:08s
118BPM
Audio by Amiata Records's display pictureAmiata Recordsverified
Remove the vocals from this track
T
Here are the isolated vocals and instrumental
play_arrow3:08s
118BPM
Audio by Amiata Records's display pictureAmiata Recordsverified

Frequently Asked Questions

What's the rate limit?

There isn't a hard limit — pricing is per-credit, and the system scales horizontally. If you're doing high volume (thousands of concurrent jobs), ping the team before you ship so we can pre-warm capacity.

How do I pass audio into the job?

Either an HTTPS URL we can fetch, or a pre-uploaded audio ID from /audio/upload. URL-based jobs are faster to start; upload-based jobs avoid rate-limiting issues when the source domain blocks server-to-server fetches.

Where does auth come from?

Admin bearer tokens only. Request one from the team with your intended use case. Do not hand out admin tokens to clients — use them server-side and expose your own scoped surface.

What's the latency per job?

Typical 3-4 minute track: 20-40 seconds end-to-end from POST to finished files. Longer tracks (10 minutes) take proportionally longer. The job is queued if GPU capacity is saturated; you can subscribe to webhooks for async notification.

What formats does it output?

WAV 44.1kHz/16-bit stems by default. Request MP3 or FLAC via the output format parameter. Original bit depth is preserved where the source allows it.

Can I separate more than four stems?

The default model returns vocals/drums/bass/other (classic 4-stem split). For a finer breakdown into guitar/keys/strings, use the advanced multi-stem model by setting modelId to the premium variant — costs more credits, runs slightly slower.

How does pricing work?

Per-credit pricing scales with duration. A 3-minute track costs roughly X credits (see docs.twoshot.app for current rates). Bulk commitments available for enterprise volume.

Is there an SDK?

Official SDKs in TypeScript and Python are published in the docs; community wrappers exist for Go and Ruby. The REST API is straightforward enough that most integrations just use fetch/httpx directly.

What about webhooks for job completion?

Pass a callback URL in the job POST; we'll hit it when the job transitions to completed or failed. Includes HMAC signature verification so you can trust it came from us.

Also try separate stems directly on TwoShot

The full separate stems experience is a free page on TwoShot — same models, no setup.

Related Integrations

Separate Stems with Kimi K2
Split a track into vocals, drums, bass, and other stems.
the TwoShot APIMake a Voiceover via the TwoShot API
Text-to-speech in any voice, any language.
MakeSeparate Stems via Make
Split a track into vocals, drums, bass, and other stems.
the TwoShot APIClone a Voice via the TwoShot API
Sub-30-second reference clip → persistent custom voice.
Separate Stems in ChatGPT
Split a track into vocals, drums, bass, and other stems.
the TwoShot APIMake a Dance Video via the TwoShot API
Photo to dance — motion-transfer your subject onto any routine.
CursorSeparate Stems in Cursor
Split a track into vocals, drums, bass, and other stems.
the TwoShot APITranscribe a Song via the TwoShot API
Lyrics, chords, or MIDI from any audio.
Separate Stems with Claude Opus 4.7
Split a track into vocals, drums, bass, and other stems.

Powerful Creative Tools

Everything you need to create, transform, and perfect your audio, images, and video

music_note

Music Creation

Create original music, beats, and sounds from text descriptions using AI. Any genre, any style.

image

Image Creation

Create stunning visuals, album covers, thumbnails, and art from text descriptions. Edit and upscale existing images.

movie

Video Creation

Create videos from text or images. Animate photos, create music videos, and produce motion content for social media.

record_voice_over

Voice Tools

Text-to-speech, voice enhancement, and vocal transformation.

call_split

Stem Separation

Isolate vocals, drums, bass, and instruments from any track in seconds.

auto_fix_high

Enhance & Clean Up

Remove background noise, upscale images, enhance video quality, and polish your media.

spatial_audio_off

Sound Effects

Generate custom SFX and foley for games, videos, and podcasts.

shuffle

Remix & Extend

Remix tracks in new styles or extend songs seamlessly with AI.

edit_note

Writing Tools

Cowrite lyrics and scripts - draft, refine, and iterate together until every line is right.

queue_music

Studio

Arrange, compose, and produce directly in your browser. Audio, video, images — all in one workspace.

library_music

Content Library

200,000+ royalty-free sounds and samples ready for commercial use.

What Will You Create?

AI tools for music, video, images, and voice

music_note

For Musicians & Producers

Turn ideas into tracks faster. Create beats, sounds, and full productions with AI assistance.

videocam

For Video Creators

Complete video production with AI. Generate videos, images, music, and voiceovers.

podcasts

For Podcasters

Studio-quality audio from any recording. Clean up interviews, enhance voices, and add music.

apartment

For Studios & Brands

Production-ready AI for audio, video, and visuals. Full rights clearance, API access, team collaboration.

Tailored Tracks

Transform your creative ideas into tangible sounds with our AI powered tools. Simply describe what you want - "fast drum & bass jungle-style drum loop" or "layered flutes inspired by nature" - and see the magic unfold.

Visual
Creation

Create stunning visuals from text descriptions. Design album covers, thumbnails, portraits, and art — all through conversation.

Demo Portrait - Woman Dramatic Lighting
Demo Portrait - Woman Dramatic LightingImage by TwoShotverified
Demo Portrait - Man Dramatic Lighting
Demo Portrait - Man Dramatic LightingImage by TwoShotverified

Motion
& Video

Create videos from text or images. Animate photos, produce music videos, and make motion content for social media.

error
Unavailable
error
Unavailable

Bring Photos
to Life

Upload any photo and watch it move. AI-powered motion control turns still images into dynamic dance videos and animations.

Demo Dance Character - Original
Demo Dance Character - OriginalImage by TwoShotverified
error
Unavailable

Transform
Any Image

Change backgrounds, remove objects, upscale resolution, and edit images through simple conversation. No Photoshop needed.

Demo Portrait - Woman Dramatic Lighting
Demo Portrait - Woman Dramatic LightingImage by TwoShotverified
Demo Portrait - Tokyo Neon Background
Demo Portrait - Tokyo Neon BackgroundImage by TwoShotverified

Your New
Cowriter

A creative partner for lyrics and scripts. Get a draft, then go back and forth - refine lines, try new angles, iterate together until it's exactly what you envisioned.

New Verse

[Verse 2] City lights blur past my window, neon dreams alive Headphones on, world fades out, feeling so alive Every beat a heartbeat, every drop a sign Lost in the rhythm, yeah this moment's mine Floating through the frequencies, sound waves intertwine Making magic happen, one bar at a time

Build Your Voice

Text-to-speech, voice enhancement, and vocal transformation. Create professional voiceovers in any style or voice.

Deconstruct
Audio

Isolate vocals, drums, bass, and instruments from any track in seconds. Perfect for remixing, sampling, or creating karaoke versions.

Enhance & Clean Up

Remove background noise, upscale images, enhance video quality, and polish your media.

Bespoke
SFX

Generate custom sound effects and foley for games, videos, and podcasts. From explosions to footsteps, create exactly what you need.

Reimagine
Sounds

Leverage the power of our AI to reimagine existing samples. Extract particular elements from a sample, or create a completely new sample based on a reference.

play_arrow

Ready for
the Studio

Arrange, compose, and produce directly in your browser with our online DAW. Drag and drop samples, add effects, and export your creations.

Enter Studio
Plugin DemoFruity LoopsAbleton LiveLogic Pro

Trusted by Industry Professionals

From Grammy-winning producers to major labels, see who's creating with TwoShot

Fuse 808 Mafia
Fuse 808 Mafiaverified
@fuse808mafia
play_circle500M+ streams
Producer
Kaelin Ellis
Kaelin Ellisverified
@kaelinellis
play_circle100M+ streams
Producer
Kenny Beats
Kenny Beatsverified
@kennybeats
play_circle1B+ streams
Producer
Sony Music
Sony Musicverified
@sonymusic
Partner
verified100% Rights-Safe for Commercial Use