NiceVois

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

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

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "NiceVois": {
      "url": "https://nicevois.com/api/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (16)

• get_training_requirements read-only

  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.

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• get_training_account read-only

  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.

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• quote_training read-only

  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.

  Parameters:

  • durationSeconds (required) — number
  • epochs (required) — integer

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• 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 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.

  Parameters:

  • fileName (required) — string — Original WAV, MP3, FLAC, M4A, or OGG filename.
  • contentType (required) — string
  • sizeBytes (required) — integer
  • durationSeconds (required) — number
  • epochs (required) — integer
  • modelName (required) — string
  • submissionId (required) — string
  • acceptsStandingAgreement — boolean — Set only when the user explicitly accepts the linked standing voice-training agreement after CONSENT_REQUIRED. Omit for accounts that have already accepted.

  Hints: read-only no · destructive no · idempotent not declared · open-world yes

• 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.

  Parameters:

  • jobId (required) — string

  Hints: read-only no · destructive no · idempotent not declared · open-world yes

• get_training_job read-only

  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.

  Parameters:

  • jobId (required) — string

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• list_training_jobs read-only

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

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• get_conversion_requirements read-only

  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.

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• list_voice_models read-only

  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.

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• 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 select the imported voice.

  Parameters:

  • fileName (required) — string — Original .pth or .zip filename.
  • sizeBytes (required) — integer

  Hints: read-only no · destructive no · idempotent not declared · open-world yes

• 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.

  Parameters:

  • modelId (required) — string — The id returned by list_voice_models.
  • fileName (required) — string — Original WAV, MP3, FLAC, M4A, or OGG vocal filename.
  • durationSeconds (required) — number — Measured duration of the source audio in seconds. NiceVois uses this to verify that the account can download the result before cloud work.
  • sizeBytes — integer — Exact byte size of the source audio. Supply it whenever the client can measure the file so interrupted uploads are verifiable and safely resumable.
  • transpose — integer — Pitch shift in semitones, from -24 through 24. Use 0 when no shift was requested.

  Hints: read-only no · destructive no · idempotent not declared · open-world yes

• get_voice_conversion read-only

  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.

  Parameters:

  • conversionId (required) — string

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• 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 before, ask before retrying and then set confirmRepeat true.

  Parameters:

  • conversionId (required) — string
  • kind (required) — string — Prefer cleaned unless the user specifically asks for standard RVC.
  • eventId — string
  • confirmRepeat — boolean — Only true after the user explicitly confirms downloading the same artifact again.

  Hints: read-only no · destructive no · idempotent not declared · open-world yes

• list_free_audio_tools read-only

  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.

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• create_free_audio_job

  Split stems, isolate vocals, or remove noise or reverb. No account needed. Each audio tool includes 10 free minutes every 24 hours; subscribers have unlimited use. Returns an upload URL, then use get_free_audio_job.

  Parameters:

  • tool (required) — string — split_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. remove_reverb: room echo and reverb out of a voice recording.
  • fileName (required) — string — The audio file's name with its extension: WAV, MP3, FLAC, M4A or OGG.
  • sizeBytes (required) — integer — The file's exact size in bytes.
  • outputFormat — string — Format of the files you get back. Use wav unless the user asks for another.
  • durationSeconds — number — The audio's length in seconds, if you can measure it. NiceVois measures the file itself after upload, so leave this out rather than guess.

  Hints: read-only no · destructive no · idempotent not declared · open-world yes

• get_free_audio_job read-only

  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.

  Parameters:

  • jobId (required) — string — The id returned by create_free_audio_job.

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

Publisher website

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.