NiceVois
Server Details
Free stem, vocal, noise, reverb and format tools. Train RVC voices; convert vocals and whole songs.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 19 tools
Several tools are near-duplicates distinguished only by tier: create_audio_job vs create_free_audio_job, get_audio_job vs get_free_audio_job, and get_audio_download vs download_voice_conversion_output all read similarly, and create_audio_job's description ('Every NiceVois audio tool') overlaps heavily with create_free_audio_job's. The free/account distinction is stated in the descriptions, but an agent must read carefully to avoid misselecting when a user has a connected account. Training and voice-conversion tools are otherwise cleanly separated.
Almost everything follows verb_noun snake_case: create_/get_/list_/download_ + resource. Minor deviations exist where the verb lacks a clear object (start_training, quote_training) and where resource nouns shift between 'audio_job', 'free_audio_job', 'training_job', and 'voice_conversion', which makes sibling tools look less parallel than they are.
19 tools span three genuine sub-domains (audio processing jobs, RVC voice conversion, private voice training), so each cluster justifies its tools. It sits at the high end of comfortable, and the parallel free/paid job pairs add two tools that could arguably be folded into one.
Each workflow has create/poll/download and helper lookups, but there are notable dead ends: no cancel/delete job tool, no list for audio or conversion jobs (only list_training_jobs exists), and training readiness is reported yet no tool fetches the completed model artifact. Agents will hit limits when a user wants to abort a job or retrieve a trained model.
Available Tools
19 toolscreate_audio_jobRun any NiceVois audio toolAInspect
Every NiceVois audio tool. With no account: split_stems, split_lead_backing, remove_noise, remove_reverb and enhance_vocal (one free use of each per network, up to five minutes) and convert_format (free). With a connected account every tool runs on that account's plan (a subscriber's unlimited use applies), including generate_harmony (upper and lower harmonies from a solo lead vocal), which needs an account. Returns an upload URL; then use get_audio_job.
Inputs: tool (required), fileName (required), sizeBytes (required), outputFormat, +1 more. Returns: id, tool, error, links, +12 more
create_free_audio_jobSplit, clean up or enhance audio (no account needed)AInspect
Split stems, isolate vocals, split lead from backing vocals, remove noise or reverb, or enhance a vocal. No account, API key or sign-up needed: one free use of each tool per network, of a file up to five minutes, as on the website. A connected account runs it on that account's plan instead. Returns an upload URL; PUT the file, then use get_free_audio_job.
Inputs: tool (required), audio, fileName, sizeBytes, +2 more. Returns: id, tool, error, links, +12 more
create_training_jobCreate an RVC training uploadAInspect
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.
Inputs: epochs (required), fileName (required), modelName (required), sizeBytes (required), +6 more. Returns: id, links, epochs, status, +14 more
create_voice_conversionCreate an RVC vocal conversionAInspect
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. Creating it counts one of the account's conversions (three free per account, each up to five minutes long; it comes back if the conversion fails); listening and downloads are free.
Inputs: modelId (required), fileName (required), durationSeconds (required), sizeBytes, +3 more. Returns: id, error, stage, status, +10 more
create_voice_model_importPrepare a private RVC model uploadAInspect
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.
Inputs: fileName (required), sizeBytes (required). Returns: id, status, upload
download_voice_conversion_outputDownload a completed voice conversionAInspect
Use after get_voice_conversion says the job is complete and the user wants the cleaned or standard output. Downloads are free; the conversion was counted once when it started. If the exact file was downloaded before, ask before retrying and then set confirmRepeat true.
Inputs: kind (required), conversionId (required), eventId, confirmRepeat. Returns: accepted, downloadUrl, downloadCount, secondsCharged
get_audio_downloadGet a download link for an audio outputAInspect
Returns a short-lived link to one output of a completed audio job. Download it or give it to the user straight away.
Inputs: jobId (required), output (required). Returns: downloadUrl
get_audio_jobCheck an audio jobARead-onlyInspect
Use after create_audio_job and the upload, until the job is completed or failed. When complete it lists each output; call get_audio_download for the ones the user wants.
Inputs: jobId (required). Returns: id, tool, error, links, +12 more
get_conversion_requirementsGet RVC voice conversion requirementsARead-onlyInspect
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.
Inputs: no named parameters. Returns: outputs, pricing, service, workflow, +5 more
get_free_audio_jobCheck a free audio jobARead-onlyInspect
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.
Inputs: jobId (required). Returns: id, tool, error, links, +12 more
get_training_accountCheck NiceVois training allowanceARead-onlyInspect
Check the connected account's free trainings, purchased training passes and subscription allowances before preparing a job. Any purchase link keeps checkout on this same account.
Inputs: no named parameters. Returns: balance, freeRuns, products, signedIn, +5 more
get_training_jobCheck an RVC training jobARead-onlyInspect
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 (required). Returns: id, links, epochs, status, +14 more
get_training_requirementsGet RVC training requirementsARead-onlyInspect
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.
Inputs: no named parameters. Returns: outputs, service, workflow, maxEpochs, +11 more
get_voice_conversionCheck an RVC vocal conversionARead-onlyInspect
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.
Inputs: conversionId (required). Returns: id, error, stage, status, +10 more
list_free_audio_toolsList the free NiceVois audio toolsARead-onlyInspect
Use this to see NiceVois's free audio tools, which need no account, no API key and no sign-up: split a song into vocals and instrumental (vocal remover, acapella, karaoke instrumental), split lead vocals from backing vocals, remove background noise, remove reverb or echo, and enhance a phone-recorded or noisy vocal (Vocal Enhancer). Returns each tool's id, the accepted formats, and a website link to give the user when you cannot upload their file yourself.
Inputs: no named parameters. Returns: price, tools, service, workflow, +5 more
list_training_jobsList private RVC training jobsARead-onlyInspect
Use this to find the authenticated user's recent NiceVois jobs before asking for a job ID they may not know.
Inputs: no named parameters. Returns: jobs, retentionDays
list_voice_modelsList private RVC voice modelsARead-onlyInspect
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.
Inputs: no named parameters. Returns: models, billing, allowance, usedToday, +1 more
quote_trainingQuote an RVC training jobBRead-onlyInspect
Call after inspecting the audio and before creating a job. Returns whether the requested training is covered, its technical limits, available pass/pack/plan offers and a private same-account purchase link if needed. Training is counted in whole trainings, not fractional-dollar amounts.
Inputs: epochs (required), durationSeconds (required), trainingEngine. Returns: epochs, canStart, currency, accountUrl, +10 more
start_trainingStart RVC trainingAInspect
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 (required). Returns: id, links, epochs, status, +14 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Audio AI tools: transcription with speakers, stems, noise removal, MIDI, speech, voices and music.
AI music studio: song generation with vocals, covers, stems, voice conversion, mastering, editing.
Make AI Tracks, loops and sound effects, split stems, build drum kits and master songs.
Make full songs with vocals, split stems, transcribe and analyze audio from your AI assistant.
Related MCP Servers
- AlicenseBqualityBmaintenanceAn AI stem separation and audio restoration partner for Ultimate Vocal Remover (UVR5). Speak in natural language to extract vocals, drums, bass, guitar and piano, combine separation models and clean up recordings, then bring the resulting stems back to your DAW. Your audio stays on your computer.341AGPL 3.0
- AlicenseAqualityDmaintenanceRemove vocals, extract instrumentals, and split any song into up to six stems — directly from Claude Desktop, Cursor, or any MCP client. Supports local audio files, YouTube URLs, and SoundCloud track1119 npmMIT
- AlicenseAqualityCmaintenanceEnables AI agents to turn song requests into ready-to-send audio files by searching and downloading tracks, trimming clips, separating vocals, applying RVC voice conversion, and mixing the result with accompaniment. Supports original-clip and full-cover modes with environment self-checks.3MIT
- AlicenseBqualityDmaintenanceProvides AI-powered audio generation and processing through the MusicGPT API, enabling music creation, voice conversion, audio manipulation, stem extraction, and audio analysis capabilities.2417 npm2MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.