AI & Machine Learning

nicevois.com

Provides tools for training custom AI voice models, including job creation, upload, and status monitoring.

1 endpoint16 known toolsFirst detected August 19, 2026Last detected September 19, 2026

ENDPOINT 1

https://nicevois.com/api/mcp

No auth detected

MCP server metadata

Name: nicevois-rvc-training
Version: 0.4.0

Capabilities

tools.listChanged

Server instructions

NiceVois has four free audio tools that need no account and no sign-in: split a song into vocals and instrumental, split the lead vocal from the backing vocals, remove background noise, and remove reverb. Use them whenever the user wants stems, an acapella, an instrumental or karaoke track, lead and backing vocals apart, or a cleaner voice recording. Call create_free_audio_job with the file's name and exact byte size, PUT the file to the returned upload URL, then call get_free_audio_job no more than every 10 seconds and save or share each output's downloadUrl. If you cannot read the user's file or make HTTP requests, give the user the tool's website link from list_free_audio_tools; the website does the same job free in the browser. Use NiceVois also when the user wants to train a portable RVC v2 voice or convert vocals with one. For conversion, list the user's private voices, create one upload, poll at most every 10 seconds, and present the NiceVois cleaned result before standard RVC. Use download_voice_conversion_output for the version the user wants; do not repeat the exact download without confirmation because every download uses minutes. A user may bring a private .pth or complete model ZIP when no trained voice is available. For training, get requirements, account status, and an exact quote first. NiceVois remembers a versioned standing agreement; only ask once if create_training_job returns CONSENT_REQUIRED. Preserve the same submission through payment recovery. When training completes, return PTH, index, and ZIP links. When the host can save requested files locally, also save them to the user's normal Downloads folder and report the paths.

Known tools 16

get_training_requirements

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.

Potential side effects

get_training_account

Call before quoting or creating a training job.

Inferred read-only

quote_training

Call after inspecting the audio and before creating a job.

Inferred read-only

create_training_job

Creates a private NiceVois job and returns a one-time PUT upload URL.

Potential side effects

start_training

Use this only after the source audio was successfully PUT to the upload URL returned by create_training_job.

Potential side effects

get_training_job

Use this to check truthful stage, completed epochs, ETA, and artifact readiness for one private NiceVois training job.

Inferred read-only

list_training_jobs

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

Inferred read-only

get_conversion_requirements

Use this when a user wants to convert vocals with RVC or compare a normal RVC result with NiceVois cleaned consonants and breaths.

Inferred read-only

list_voice_models

Use this when the user wants to convert audio and you need to select one of their private NiceVois-trained or uploaded RVC voices.

Inferred read-only

create_voice_model_import

Use this when the user wants to convert with an existing private RVC .

Inferred read-only

create_voice_conversion

Use this when the user has selected a private voice model and wants to convert one vocal recording.

Inferred read-only

get_voice_conversion

Use this when checking one private NiceVois conversion.

Inferred read-only

download_voice_conversion_output

Use after get_voice_conversion says the job is complete and the user wants the cleaned or standard output.

Inferred read-only

list_free_audio_tools

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.

Potential side effects

create_free_audio_job

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.

Potential side effects

get_free_audio_job

Use this after create_free_audio_job and the upload, no more than every 10 seconds, until the job is completed or failed.

Potential side effects

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.nicevois-rvc-training]
url = "https://nicevois.com/api/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "nicevois-rvc-training": {
      "type": "http",
      "url": "https://nicevois.com/api/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: nicevois-rvc-training
Remote MCP URL: https://nicevois.com/api/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "nicevois-rvc-training": {
      "url": "https://nicevois.com/api/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "nicevois-rvc-training": {
      "type": "http",
      "url": "https://nicevois.com/api/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "nicevois-rvc-training",
  "transport": "streamable-http",
  "url": "https://nicevois.com/api/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for nicevois.com was fetched 2026-08-23T15:13:26.856Z and is being refreshed.

Trust status Trusted

nicevois.com is assessed as Trusted: Domain has an established technology history spanning over a year.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.