← Back to directory

Split up to 45 s of music into a vocal stem and an accompaniment stem (Spleeter ...

https://ton.halowerk.com/v1/stem-split

Overview

Split up to 45 s of music into a vocal stem and an accompaniment stem (Spleeter 2stems on CPU) and return both as MP3 or Opus, with per-second levels. Decodes up to 45 s to 44.1 kHz stereo (mono is duplicated) and runs Deezer Spleeter 2stems (U-Net, MIT licence) as ONNX: the export made with the sherpa-onnx conversion scripts (Apache-2.0), int8, repository csukuangfj/sherpa-onnx-spleeter-2stems-int8 at revision f315b4e, SHA-256 checked.

Protocol x402 (POST)
Price $0.02
Payment Asset USD Coin
Payment Network eip155:8453
Category uncategorized
Provider ton
Source bazaar
Indexed 2026-11-21 08:10:21

Health

Status unknown
Latency (p50) —
Uptime (30d) —
Reliability Score —
Last Checked Never
Last Healthy Never
Consecutive Failures 0

x402 Payment Validation

Payment Requirements —
Asset Verified —
Facilitator —

Input Schema

{ "body": { "audio_url": "https://ton.halowerk.com/beispiel/stem-split-audio.ogg" }, "bodyType": "json", "method": "POST", "type": "http" }

Output Schema

{ "example": { "limitations": [ "The vocal stem contains nothing above 11.025 kHz (model bandwidth); sibilants above that remain in the accompaniment.", "Separation quality is that of Spleeter 2stems (2019); expect bleeding of instruments into the vocal stem and vice versa.", "At most 45 s of audio per call; responses carry both stems as base64." ], "result": { "channels": 2, "duration_s": 6.14, "model": { "license": "MIT (Deezer Spleeter 2stems weights); ONNX export via sherpa-onnx scripts (Apache-2.0)", "name": "Spleeter 2stems", "onnx": "vocals.int8.onnx, accompaniment.int8.onnx", "repo": "csukuangfj/sherpa-onnx-spleeter-2stems-int8", "revision": "f315b4e" }, "sample_rate": 44100, "source": { "analysed_s": 6.14, "analysis_rate_hz": 44100, "bytes": 24356, "channels": 1, "codec": "opus", "container": "ogg", "duration_s": 6.147, "sample_rate": 48000, "sha256": "849f5e5455dd89857fa2dcfdd6866ab929fb9f328de66c79fb5f9918449a0277" }, "stems": [ { "audio_base64": "SUQzBAAAAAAACgAAAAAAAAAAAAD/+7BkAA4EqCk8k1h6cC3FFZIwYi4UCKL2bmsngR8UVlmBvXgABaVaQgjOHAIHNfJOaxHUhrByCMHAEtTSVMoyCRwekElDhsrl0fk7KIOjcNoyCTwQJDRQQdCBnt2ZZONLWunoW0X4jegu67wACcIOpF2ZwSAyEyAlgNBIzzY3Ojw5FA2MlHiLONENCHrEPcDV/ez8eD4Ph93AYPg+D4fBAEAQDBf3dPggCAIAgAwfB8Hw+CAIAgcT7gFTCA5AmbtwCLHd3d3d0RERERHd3Oc53I39/5yEIACGnOr+uhCQgAQQwY///6CbqHKcQvM/zlzb2+P1MQxQhDGaEMLJE3JUxhUVTgh8wgxYA4ggEExEfHpwEEmdHq7Y… [truncated, 198140 chars]", "bytes": 148604, "format": "mp3", "mime_type": "audio/mpeg", "name": "vocals", "rms_dbfs_per_second": [ -21.7, -23.8, -20.4, -19.8, -21.1, -22.9, -34.5 ] }, { "audio_base64": "SUQzBAAAAAAACgAAAAAAAAAAAAD/+7BkAA8VAj46A2F7Yi3FFZIwYi4W9QTmDqNNiSqUVl2BvXg8k1NymANYKiVtAQOuYswwR+4m78/XzGP//9DGMYxjGwAABAVHdTofPmEWxCCeEIVh0DvDrE8Kwg59HOj1IuULRY41wIWSep7AZDFG+AXgS5Aww0fKW8ogIBbRxpTDeo4FbPNQE4oEWZbYyeAzyKya8OO/4AAAAYeHh4eAAAAAAYeHh4eAAAAAAYeHh48AAAAARh4eHjwAAAABUPD/93/+wFTCE6AgaMQi5URERERHd3d3d0REIQhGO/9v5DnOBi3kIjempzw4GcW4f///6TnmHjfGITCgHzCQFwwBTBoETEkSjBoB3RfZpyWlyNUwsLCwqKqq… [truncated, 198140 chars]", "bytes": 148604, "format": "mp3", "mime_type": "audio/mpeg", "name": "accompaniment", "rms_dbfs_per_second": [ -62.4, -55.8, -61.8, -61.8, -58.4, -62.5, -76.1 ] } ], "vocal_to_accompaniment_db": 38.2 }, "service": "stem-split", "status": "success" }, "type": "json" }