Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

NiceVois

REMOTE · NICEVOIS.COM · SCANNED SEP 21

Free stem, lead/backing vocal, noise and reverb splitting, no account. Train and use RVC voices.

Available components

+1 this week 86 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security80
Transport & Reachability100
Schema Quality & AI Usability74
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 1841 tokens (~115/item across 16 items; 16 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management96
  • Stability check failed: schema churn in the 30 days we've observed: 0 tool removals, 1 breaking changes, 0 auth/transport breaks, 4 additions. See how to fix → Fail
Tool Coverage87
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 53% of tool parameters carry a description.Partial
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 16 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 17 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the NiceVois MCP server?

NiceVois is a hosted endpoint at https://nicevois.com/api/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · nicevois.com

# add to Claude Code
claude mcp add --transport http com-nicevois-rvc-training 'https://nicevois.com/api/mcp'
// .cursor/mcp.json
{
  "mcpServers": {
    "com-nicevois-rvc-training": {
      "url": "https://nicevois.com/api/mcp"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "com-nicevois-rvc-training": {
      "type": "http",
      "url": "https://nicevois.com/api/mcp"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.com-nicevois-rvc-training]
url = "https://nicevois.com/api/mcp"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-nicevois-rvc-training": {
      "type": "remote",
      "url": "https://nicevois.com/api/mcp",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add com-nicevois-rvc-training --url 'https://nicevois.com/api/mcp' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  com-nicevois-rvc-training:
    url: "https://nicevois.com/api/mcp"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "com-nicevois-rvc-training": {
      "Transport": "http",
      "Url": "https://nicevois.com/api/mcp"
    }
  }
}
# add to Vellum
assistant mcp add com-nicevois-rvc-training -t streamable-http -u 'https://nicevois.com/api/mcp'
// mcp.json
{
  "mcpServers": {
    "com-nicevois-rvc-training": {
      "type": "http",
      "url": "https://nicevois.com/api/mcp"
    }
  }
}

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 21 Sept 26 0
    • Stability: pass → fail security
  • 18 Sept 26 0
    • Tool “create_image_training_job” was removed security
    • Tool “get_image_training_job” was removed security
    • Tool “get_image_training_requirements” was removed security
    • Tool “quote_image_training” was removed security
    • Tool “start_image_training” was removed security
    • The server rewrote its instructions, which are the text every model session reads security
    • Schema quality: pass → fail functional
    • Tool coverage: 47% → 53% functional
    • Server version: 0.3.0 → 0.4.0 functional
    • New tool “create_free_audio_job” functional
    • New tool “get_free_audio_job” functional
    • New tool “list_free_audio_tools” functional
  • 17 Sept 26 0
    • Stability: 0.97 → pass security
    • Tool “create_image_training_job” rewrote its description, which is the text the model reads security
  • 16 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 14 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

  • 12 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

  • 10 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

  • 7 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Sept 2026 · Probed https://nicevois.com/api/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=nicevois.com CN=YR2,O=Let's Encrypt,C=US 7 Aug 2026 5 Nov 2026 RSA 2048 SHA256-RSA 5dd481b4533c596825466ec71ab7e7de208
SANs: nicevois.com, www.nicevois.com
CN=YR2,O=Let's Encrypt,C=US (CA) CN=Root YR,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 RSA 2048 SHA256-RSA 4ebd24947e24d394802d84a52fd5b319
CN=Root YR,O=ISRG,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 RSA 4096 SHA256-RSA f24b6d17f9d9ad7cb1c9fea78782699f

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of nicevois.com. Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
com. present 19718 13 Verified
nicevois.com. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=63072000

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://nicevois.com/api/mcp Verified 200
http (plaintext) http://nicevois.com/api/mcp HTTPS enforced 308 https://nicevois.com/api/mcp
MCP tools · 16 exposed · ~1,495 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
create_free_audio_job ~263

Use this when the user wants to split a song into stems (vocals and instrumental), isolate or remove vocals, make an acapella or a karaoke instrumental, split the lead vocal from the backing vocals, or remove background noise or reverb from a recording. Free, no account. Returns a one-time upload URL: PUT the file's bytes to it, then call get_free_audio_job with the returned id.

NameTypeReqDescription
durationSecondsnumberThe audio's length in seconds, if you can measure it. NiceVois measures the file itself after upload, so leave this out rather than guess.
fileNamestringyesThe audio file's name with its extension: WAV, MP3, FLAC, M4A or OGG.
outputFormatstringFormat of the files you get back. Use wav unless the user asks for another.
sizeBytesintegeryesThe file's exact size in bytes.
toolstringyessplit_stems: vocals and instrumental. split_lead_backing: lead vocal, backing vocals, instrumental, and the instrumental with backing vocals. remove_noise: background noise out of a voice recording.…
NameTypeReqDescription
createdAt
durationSeconds
error
fileName
idstringyes
linksobjectyes
message
outputsarrayyes
pollAfterSecondsyes
pricestringyes
stage
statusstringyes
toolstringyes
toolNamestringyes
uploadyes
websiteUrlstringyes

No examples provided.

create_training_job ~202

Creates a private NiceVois job and returns a one-time PUT upload URL. Do not ask for consent before the first attempt because NiceVois remembers the current standing account agreement. If the server returns CONSENT_REQUIRED, ask for one acceptance of the linked standing agreement and retry once with acceptsStandingAgreement=true. This allocates a private training slot but does not start GPU work until the audio is uploaded and start_training is called.

NameTypeReqDescription
acceptsStandingAgreementbooleanSet only when the user explicitly accepts the linked standing voice-training agreement after CONSENT_REQUIRED. Omit for accounts that have already accepted.
contentTypestringyes
durationSecondsnumberyes
epochsintegeryes
fileNamestringyesOriginal WAV, MP3, FLAC, M4A, or OGG filename.
modelNamestringyes
sizeBytesintegeryes
submissionIdstringyes
NameTypeReqDescription
artifactsyes
completedAt
createdAt
currentEpoch
durationSeconds
epochs
estimatedCompletionAt
estimatedRemainingSeconds
etaText
expiresAt
idstringyes
linksobjectyes
message
modelName
startedAt
statusstringyes
updatedAt
uploadyes

No examples provided.

create_voice_conversion ~191

Use this when the user has selected a private voice model and wants to convert one vocal recording. Returns a private upload instruction. Upload only the source vocal, then call get_voice_conversion with the same conversion ID.

NameTypeReqDescription
durationSecondsnumberyesMeasured duration of the source audio in seconds. NiceVois uses this to verify that the account can download the result before cloud work.
fileNamestringyesOriginal WAV, MP3, FLAC, M4A, or OGG vocal filename.
modelIdstringyesThe id returned by list_voice_models.
sizeBytesintegerExact byte size of the source audio. Supply it whenever the client can measure the file so interrupted uploads are verifiable and safely resumable.
transposeintegerPitch shift in semitones, from -24 through 24. Use 0 when no shift was requested.
NameTypeReqDescription
createdAt
error
fileName
idstringyes
modelName
outputsyes
providerState
restoration
stage
stageMessage
statusstringyes
timings
transpose
uploadyes

No examples provided.

create_voice_model_import ~87

Use this when the user wants to convert with an existing private RVC .pth file or complete model ZIP instead of a voice trained in their NiceVois library. Returns a one-time PUT upload instruction. After uploading, call list_voice_models to select the imported voice.

NameTypeReqDescription
fileNamestringyesOriginal .pth or .zip filename.
sizeBytesintegeryes
NameTypeReqDescription
idstringyes
statusstringyes
uploadobjectyes

No examples provided.

download_voice_conversion_output ~119

Use after get_voice_conversion says the job is complete and the user wants the cleaned or standard output. Each download uses the source audio's duration from the account's conversion-download minutes. If the exact file was downloaded before, ask before retrying and then set confirmRepeat true.

NameTypeReqDescription
confirmRepeatbooleanOnly true after the user explicitly confirms downloading the same artifact again.
conversionIdstringyes
eventIdstring
kindstringyesPrefer cleaned unless the user specifically asks for standard RVC.
NameTypeReqDescription
acceptedbooleanyes
downloadCountintegeryes
downloadUrlstringyes
secondsChargedintegeryes

No examples provided.

get_conversion_requirements ~58

Use this when a user wants to convert vocals with RVC or compare a normal RVC result with NiceVois cleaned consonants and breaths. Returns the real input formats, model choices, workflow, current free-beta policy, and outputs.

Input schema present but exposes no named parameters.

NameTypeReqDescription
authenticationstringyes
modelInputsarrayyes
outputsarrayyes
pricingobjectyes
servicestringyes
sourceAudioFormatsarrayyes
transposeSemitonesobjectyes
wholeSongCoverobjectyes
workflowarrayyes

No examples provided.

get_free_audio_job ~78

Use this after create_free_audio_job and the upload, no more than every 10 seconds, until the job is completed or failed. When it completes, it lists every output file (for example lead vocal, backing vocals, instrumental) with a download link.

NameTypeReqDescription
jobIdstringyesThe id returned by create_free_audio_job.
NameTypeReqDescription
createdAt
durationSeconds
error
fileName
idstringyes
linksobjectyes
message
outputsarrayyes
pollAfterSecondsyes
pricestringyes
stage
statusstringyes
toolstringyes
toolNamestringyes
uploadyes
websiteUrlstringyes

No examples provided.

get_training_account ~49

Call before quoting or creating a training job. Returns the connected account's welcome-credit status, available and reserved balance, balance packs, and a private browser link that keeps checkout on this same agent identity.

Input schema present but exposes no named parameters.

NameTypeReqDescription
accountUrl
balanceyes
checkoutEnabledbooleanyes
freeRunMaxDurationSecondsinteger
freeRunMaxEpochsinteger
freeRunsobjectyes
freeTrainingboolean
productsarray
signedInboolean

No examples provided.

get_training_job ~55

Use this to check truthful stage, completed epochs, ETA, and artifact readiness for one private NiceVois training job. Poll reasonably; do not call more often than every 15 seconds.

NameTypeReqDescription
jobIdstringyes
NameTypeReqDescription
artifactsyes
completedAt
createdAt
currentEpoch
durationSeconds
epochs
estimatedCompletionAt
estimatedRemainingSeconds
etaText
expiresAt
idstringyes
linksobjectyes
message
modelName
startedAt
statusstringyes
updatedAt
uploadyes

No examples provided.

get_training_requirements ~43

Use this before training an AI voice to confirm NiceVois input formats, duration and epoch limits, consent requirements, outputs, retention, and the exact upload workflow.

Input schema present but exposes no named parameters.

NameTypeReqDescription
agreementUrlstringyes
authenticationstringyes
consentModelstringyes
consentVersionstringyes
freeAllowanceobjectyes
maxAudioBytesnumberyes
maxDurationSecondsnumberyes
maxEpochsnumberyes
minEpochsnumberyes
outputsarrayyes
paidTrainingobjectyes
retentionDaysnumberyes
servicestringyes
supportedFormatsarrayyes
workflowarrayyes

No examples provided.

get_voice_conversion ~71

Use this when checking one private NiceVois conversion. Poll no more than once every 10 seconds. Report the returned stage without inventing progress. When complete, present the NiceVois cleaned version first and use download_voice_conversion_output for the version the user requests.

NameTypeReqDescription
conversionIdstringyes
NameTypeReqDescription
createdAt
error
fileName
idstringyes
modelName
outputsyes
providerState
restoration
stage
stageMessage
statusstringyes
timings
transpose
uploadyes

No examples provided.

list_free_audio_tools ~89

Use this to see NiceVois's free audio tools (no account needed): split a song into vocals and instrumental (vocal remover, acapella, karaoke instrumental), split lead vocals from backing vocals, remove background noise, and remove reverb or echo. Returns each tool's id, the accepted formats, and a website link to give the user when you cannot upload their file yourself.

Input schema present but exposes no named parameters.

NameTypeReqDescription
accountRequiredbooleanyes
inputFormatsarrayyes
maxAudioBytesintegeryes
noFileAccessstringyes
outputFormatsarrayyes
pricestringyes
servicestringyes
toolsarrayyes
workflowarrayyes

No examples provided.

list_training_jobs ~32

Use this to find the authenticated user's recent NiceVois jobs before asking for a job ID they may not know.

Input schema present but exposes no named parameters.

NameTypeReqDescription
jobsarrayyes
retentionDays

No examples provided.

list_voice_models ~49

Use this when the user wants to convert audio and you need to select one of their private NiceVois-trained or uploaded RVC voices. Do not ask for a model ID before calling this tool.

Input schema present but exposes no named parameters.

NameTypeReqDescription
allowance
billingyes
dailyLimit
modelsarrayyes
usedTodayintegeryes

No examples provided.

quote_training ~64

Call after inspecting the audio and before creating a job. Returns the exact payable amount, current balance, welcome-credit effect, shortfall, feasibility, and the private balance-page link when more balance is needed.

NameTypeReqDescription
durationSecondsnumberyes
epochsintegeryes
NameTypeReqDescription
accountUrl
balanceAfterCentsinteger
balanceBeforeCentsinteger
canStartbooleanyes
currencystringyes
durationSecondsnumberyes
epochsintegeryes
freeRunAppliedbooleanyes
payableCentsintegeryes
quotedPriceCentsinteger
recommendedProduct
shortfallCentsintegeryes
subscriptionCreditAppliedCentsinteger
subscriptionCreditRemainingCentsinteger

No examples provided.

start_training ~45

Use this only after the source audio was successfully PUT to the upload URL returned by create_training_job. Starts the private cloud RVC training job.

NameTypeReqDescription
jobIdstringyes
NameTypeReqDescription
artifactsyes
completedAt
createdAt
currentEpoch
durationSeconds
epochs
estimatedCompletionAt
estimatedRemainingSeconds
etaText
expiresAt
idstringyes
linksobjectyes
message
modelName
startedAt
statusstringyes
updatedAt
uploadyes

No examples provided.

Common questions

What is the NiceVois MCP server?

NiceVois is an MCP server listed in the public MCP registry as com.nicevois/rvc-training. Free stem, lead/backing vocal, noise and reverb splitting, no account. Train and use RVC voices. This page covers its hosted endpoint (https://nicevois.com/api/mcp).

Is the NiceVois MCP server safe to use?

NiceVois scores 86 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the NiceVois MCP server expose?

NiceVois exposes 16 tools: get_training_requirements, get_training_account, quote_training, create_training_job, start_training, and 11 more. Their descriptions and schemas cost roughly 1,495 tokens of context every time the server is loaded.

Does the NiceVois MCP server require authentication?

No. We connected to NiceVois without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the NiceVois MCP server still maintained?

NiceVois is still listed as active in the MCP registry. We last reached this channel on 21 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.