Connect NiceVois and your agent gets 18 tools, among them create_image_training_job, create_training_job, create_voice_conversion. It answers at https://nicevois.com/api/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 10 of 10 times since 5 September 2026; the last check, on 18 October 2026, succeeded.
Free stem, vocal, noise, reverb and format tools. Train RVC voices; convert vocals and whole songs.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
create_image_training_job | Use after quote_image_training. Declares the images by name and size and returns one PUT upload URL per image slot. Upload every image before calling start_image_training. The first run per account is free; later runs reserve the quoted pri Inputs: modelName, subjectType, steps, images |
create_training_job | 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 acc Inputs: fileName, contentType, sizeBytes, durationSeconds, epochs, modelName |
create_voice_conversion | 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. Inputs: modelId, fileName, sizeBytes, durationSeconds, transpose |
create_voice_model_import | 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 Inputs: fileName, sizeBytes |
download_voice_conversion_output | 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 befor Inputs: conversionId, kind, confirmRepeat, eventId |
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. Returns the real input formats, model choices, workflow, current free-beta policy, and outputs. |
get_image_training_job | Use this to check truthful stage, progress percent, ETA, and the download link for one image training job. Poll reasonably; do not call more often than every 20 seconds - a typical run takes 20 to 60 minutes. Inputs: jobId |
get_image_training_requirements | Use this when a user wants to train an image LoRA (a portable .safetensors style/subject model) from their own images without a local GPU. Returns the real image formats, counts, step range, base model, workflow, and pricing. |
get_training_account | 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. |
get_training_job | 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. Inputs: jobId |
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. |
get_voice_conversion | 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_conversi Inputs: conversionId |
list_training_jobs | Use this to find the authenticated user's recent NiceVois jobs before asking for a job ID they may not know. |
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. Do not ask for a model ID before calling this tool. |
quote_image_training | Use this before creating an image training job. Returns the exact price for the requested steps and image count, whether the account's free run is still available, and whether the current balance covers it. Inputs: steps, imageCount |
quote_training | 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. Inputs: durationSeconds, epochs |
start_image_training | Use this only after every image was successfully PUT to its upload URL from create_image_training_job. Starts the isolated cloud GPU training run. Inputs: jobId |
start_training | 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. Inputs: jobId |
Every block below points at https://nicevois.com/api/mcp. Pick your client and copy.
claude mcp add --transport http nicevois https://nicevois.com/api/mcp
{
"mcpServers": {
"nicevois": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://nicevois.com/api/mcp"]
}
}
}{
"mcpServers": {
"nicevois": {
"url": "https://nicevois.com/api/mcp"
}
}
}{
"servers": {
"nicevois": {
"type": "http",
"url": "https://nicevois.com/api/mcp"
}
}
}{
"context_servers": {
"nicevois": {
"url": "https://nicevois.com/api/mcp"
}
}
}{
"mcpServers": {
"nicevois": {
"serverUrl": "https://nicevois.com/api/mcp"
}
}
}{
"mcpServers": {
"nicevois": {
"url": "https://nicevois.com/api/mcp"
}
}
}name: NiceVois
version: 0.0.1
schema: v1
mcpServers:
- name: NiceVois
type: streamable-http
url: https://nicevois.com/api/mcp{
"mcpServers": {
"nicevois": {
"httpUrl": "https://nicevois.com/api/mcp"
}
}
}{
"mcpServers": {
"nicevois": {
"type": "http",
"url": "https://nicevois.com/api/mcp"
}
}
}{
"mcpServers": {
"nicevois": {
"url": "https://nicevois.com/api/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fnicevois.com%2Fapi%2Fmcp&type=streamable_http&id=nicevois&name=NiceVois
It answered our last check on 18 October 2026 in 248 ms. Over 10 checks since 5 September 2026 it answered 10. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by nicevois.com and served from nicevois.com, the vendor's own domain: https://nicevois.com/api/mcp.
18, as returned by the server's own tools/list on 31 August 2026: create_image_training_job, create_training_job, create_voice_conversion, create_voice_model_import, download_voice_conversion_output, get_conversion_requirements, get_image_training_job, get_image_training_requirements, and 10 more.
It answered our last check on 18 October 2026 in 248 ms. Over 10 checks since 5 September 2026 it answered 10.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://nicevois.com/api/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: com.nicevois. Endpoint host: nicevois.com. ARD identifier: urn:air:com.nicevois:mcp:rvc-training.
First indexed 31 August 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.