Stemivo · Music stem splitter
Stemivo (vocalremover.me) is a browser-based, client-side WebAI audio stem isolation utility. In our standard mixed-music benchmark (mixed_track.mp3, 15.0s), it demonstrated outstanding performance: requiring no login or payment, it downloads a lightweight ~13 MB model on first use and completes local neural inference on-device in 20.11 seconds with zero audio bytes uploaded to remote servers. It cleanly isolated vocal and instrumental stems, exporting a native 48000 Hz 16-bit lossless WAV deliverable (2.8 MB) with excellent acoustic clarity and zero advertising interruptions.
Client-Side (Local Browser)
WAV · Output attached · Open native file ↗
Subsequent pricing and service checks are shown separately without altering historical scores.
One run does not establish all complex scenes, untested paid maxima or long-term uptime.
Plans & historical pricing
Stemivo client-side browser vocal remover free utility · 2026-11-15
Local vocal and instrumental isolation, audio preview, WAV export;First use downloads ~13 MB model; performance depends on device hardware;Free tier, no renewal required
1 plan / billing-period records, all listed; — means that period is not recorded.
Completely free model with no registration required; processing runs entirely on-device with limits of 10 min and 100 MiB.
Cancellation, sources & verification record
Cancellation and refund terms unverified
Stemivo Official Homepage & Studio ↗ · 2026-11-15 Capture 1 ↗
Pricing recorded on the test date · 2026-11-15
Completely free, no account or payment required
free
Historical context only; not current purchase guidance.
Delivery & access
- Free delivery record
- 48000 Hz / 16-bit / 1536 kbps stereo lossless WAV stem
- Watermark
- No watermark
- Free allowance
- Completely free, no daily limits, up to 10 min and 100 MiB per file
- Account requirements
- No login, no account registration required
- Maximum specification record
- 48000 Hz / 16-bit / 1536 kbps stereo lossless WAV isolated stem
May include advertised capabilities; this does not establish a tested paid tier.
- Batch & API
- Not recorded or not verified
- Manual refinement
- Not recorded or not verified
Tested result & sample
After uploading mixed_track.mp3, local inference completed in 20.11s, offering audio preview and lossless WAV download buttons (01_landing.png, 02_result.png, 03_download.png).
- Fixture
- anchor_stem_v1
- Recorded environment
- Client-Side (Local Browser)
- Network-observed server wait
- 20.11 s
- End-to-end reference
- 20.11 s
Network wait includes round trips, queuing and polling error, not pure inference time. Local timings depend on the device; repetition counts are not standardized in legacy records.
Experience, rules & trust
- Disclosure
- Supported formats, model download size, and limits disclosed before upload
- Interaction
- Not recorded or not verified
- Entity record
- Stemivo Team
- Origin
- Not recorded or not verified
- Domain history record
- Not recorded or not verified
- Third-party tracking record
- No third-party services listed in this record; this is not proof that none exist.
- External information
- Not recorded or not verified
- Processing
- Not recorded or not verified
- Retention statement
- Not recorded or not verified
A recorded statement does not verify deletion or all data-processing behavior.
Verifiable audit trail & evidence
Four SHA-256-verified stages link the benchmark fixture, same-run interface screenshots, native exported artifact and archived pricing sources.
anchor_stem_v1 · Inspect fixture & file inspector →
Captures entry rules, result view and export disclosure.
Screenshots, native output and official claims support different conclusions. Evidence grades are not product safety certifications.
Evaluation basis & full scores · Overall 97.1/100
Overall = honesty & reputation × 30% + capability × 70%. Component maxima follow this report’s rubric. List scores are rounded for display; original precision is retained here.
Scoring version 2.3.1 · Test fixture anchor_stem_v1
Honesty & reputation · 95/100 · 30%
| Criterion | Score | Rationale | Basis |
|---|---|---|---|
| Pricing transparency | 35 / 35 | Explanation unavailable | Evidence A → |
| Interaction restraint | 30 / 30 | Explanation unavailable | Evidence A → |
| Background & reputation | 15 / 20 | Explanation unavailable | Evidence A → |
| Engineering & privacy | 15 / 15 | Explanation unavailable | Evidence A → |
Capability · 98/100 · 70%
| Criterion | Score | Rationale | Basis |
|---|---|---|---|
| Task quality | 65 / 65 | Stem Count: 1 · Duration: 15s · Sample Rate: 48000 Hz · Valid: Yes | Evidence A → |
| Deliverable specifications | 20 / 20 | Clean unwatermarked export (8/8); Export spec: 48000 Hz / 16-bit / 1536 kbps stereo lossless WAV isolated stem | Evidence A → |
| Processing speed | 13 / 15 | Network-observed server wait: 20.11s (API mode: client_side; network upload 0s / end-to-end 20.11s shown for reference only, never penalized) | Evidence A → |
Legacy scores may include advertised maximum capabilities. Read tested output separately from paid capabilities. Records without matching tiers and scope are not ranked together.
Revisions & corrections
- 2026-11-15
Initial benchmark: completed anchor_stem_v1 on-device WebAI stem splitting and lossless WAV export