com.nicevois/rvc-training

Est-ce que com.nicevois/rvc-training est sûr ?

Au dernier audit MCP Hub, le serveur MCP « com.nicevois/rvc-training » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 16 outils

• create_free_audio_job≈ 884 tokens

  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.

  Paramètres, retour & exemple (5)

  Paramètres

  • tool · string · requis · split_stems | split_lead_backing | remove_noise | remove_reverb
    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 · string · requis
    The audio file's name with its extension: WAV, MP3, FLAC, M4A or OGG.
  • sizeBytes · integer · requis
    The file's exact size in bytes.
  • outputFormat · string · optionnel · wav | flac | mp3 | ogg
    Format of the files you get back. Use wav unless the user asks for another.
  • durationSeconds · number · optionnel
    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.

  Exemple d'appel

  {"name": "create_free_audio_job", "arguments": {"tool": "split_stems", "fileName": "texte", "sizeBytes": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "tool": "texte", "error": "texte", "links": {}, "price": "texte", "stage": "texte", "status": "texte", "upload": "texte", "message": "texte", "outputs": [], "fileName": "texte", "toolName": "texte"}}

• create_training_job≈ 1082 tokens

  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.

  Paramètres, retour & exemple (8)

  Paramètres

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

  Exemple d'appel

  {"name": "create_training_job", "arguments": {"epochs": 1, "fileName": "texte", "modelName": "texte", "sizeBytes": 1, "contentType": "texte", "submissionId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "links": {}, "epochs": "texte", "status": "texte", "upload": "texte", "etaText": "texte", "message": "texte", "artifacts": "texte", "createdAt": "texte", "expiresAt": "texte", "modelName": "texte", "startedAt": "texte"}}

• create_voice_conversion≈ 900 tokens

  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.

  Paramètres, retour & exemple (5)

  Paramètres

  • modelId · string · requis
    The id returned by list_voice_models.
  • fileName · string · requis
    Original WAV, MP3, FLAC, M4A, or OGG vocal filename.
  • sizeBytes · integer · optionnel
    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 · optionnel
    Pitch shift in semitones, from -24 through 24. Use 0 when no shift was requested.
  • durationSeconds · number · requis
    Measured duration of the source audio in seconds. NiceVois uses this to verify that the account can download the result before cloud work.

  Exemple d'appel

  {"name": "create_voice_conversion", "arguments": {"modelId": "texte", "fileName": "texte", "durationSeconds": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "error": "texte", "stage": "texte", "status": "texte", "upload": "texte", "outputs": "texte", "timings": "texte", "fileName": "texte", "createdAt": "texte", "modelName": "texte", "transpose": "texte", "restoration": "texte"}}

• create_voice_model_import≈ 338 tokens

  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.

  Paramètres, retour & exemple (2)

  Paramètres

  • fileName · string · requis
    Original .pth or .zip filename.
  • sizeBytes · integer · requis

  Exemple d'appel

  {"name": "create_voice_model_import", "arguments": {"fileName": "texte", "sizeBytes": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "status": "texte", "upload": {}}}

• download_voice_conversion_output≈ 392 tokens

  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.

  Paramètres, retour & exemple (4)

  Paramètres

  • kind · string · requis · cleaned | normal
    Prefer cleaned unless the user specifically asks for standard RVC.
  • eventId · string · optionnel
  • conversionId · string · requis
  • confirmRepeat · boolean · optionnel
    Only true after the user explicitly confirms downloading the same artifact again.

  Exemple d'appel

  {"name": "download_voice_conversion_output", "arguments": {"kind": "cleaned", "conversionId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"accepted": true, "downloadUrl": "texte", "downloadCount": 1, "secondsCharged": 1}}

• get_conversion_requirements≈ 610 tokens

  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.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_conversion_requirements", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"outputs": [], "pricing": {}, "service": "texte", "workflow": [], "modelInputs": [], "authentication": "texte", "wholeSongCover": {}, "sourceAudioFormats": [], "transposeSemitones": {}}}

• get_free_audio_job≈ 638 tokens

  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.

  Paramètres, retour & exemple (1)

  Paramètres

  • jobId · string · requis
    The id returned by create_free_audio_job.

  Exemple d'appel

  {"name": "get_free_audio_job", "arguments": {"jobId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "tool": "texte", "error": "texte", "links": {}, "price": "texte", "stage": "texte", "status": "texte", "upload": "texte", "message": "texte", "outputs": [], "fileName": "texte", "toolName": "texte"}}

• get_training_account≈ 620 tokens

  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.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_training_account", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"balance": "texte", "freeRuns": {}, "products": [], "signedIn": true, "accountUrl": "texte", "freeTraining": true, "checkoutEnabled": true, "freeRunMaxEpochs": 1, "freeRunMaxDurationSeconds": 1}}

• get_training_job≈ 802 tokens

  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.

  Paramètres, retour & exemple (1)

  Paramètres

  • jobId · string · requis

  Exemple d'appel

  {"name": "get_training_job", "arguments": {"jobId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "links": {}, "epochs": "texte", "status": "texte", "upload": "texte", "etaText": "texte", "message": "texte", "artifacts": "texte", "createdAt": "texte", "expiresAt": "texte", "modelName": "texte", "startedAt": "texte"}}

• get_training_requirements≈ 682 tokens

  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.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_training_requirements", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"outputs": [], "service": "texte", "workflow": [], "maxEpochs": 1, "minEpochs": 1, "agreementUrl": "texte", "consentModel": "texte", "paidTraining": {}, "freeAllowance": {}, "maxAudioBytes": 1, "retentionDays": 1, "authentication": "texte"}}

• get_voice_conversion≈ 693 tokens

  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.

  Paramètres, retour & exemple (1)

  Paramètres

  • conversionId · string · requis

  Exemple d'appel

  {"name": "get_voice_conversion", "arguments": {"conversionId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "error": "texte", "stage": "texte", "status": "texte", "upload": "texte", "outputs": "texte", "timings": "texte", "fileName": "texte", "createdAt": "texte", "modelName": "texte", "transpose": "texte", "restoration": "texte"}}

• list_free_audio_tools≈ 420 tokens

  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.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_free_audio_tools", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"price": "texte", "tools": [], "service": "texte", "workflow": [], "inputFormats": [], "noFileAccess": "texte", "maxAudioBytes": 1, "outputFormats": [], "accountRequired": true}}

• list_training_jobs≈ 812 tokens

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

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_training_jobs", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"jobs": [], "retentionDays": "texte"}}

• list_voice_models≈ 452 tokens

  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.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_voice_models", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"models": [], "billing": "texte", "allowance": "texte", "usedToday": 1, "dailyLimit": "texte"}}

• quote_training≈ 586 tokens

  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.

  Paramètres, retour & exemple (2)

  Paramètres

  • epochs · integer · requis
  • durationSeconds · number · requis

  Exemple d'appel

  {"name": "quote_training", "arguments": {"epochs": 1, "durationSeconds": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"epochs": 1, "canStart": true, "currency": "texte", "accountUrl": "texte", "payableCents": 1, "freeRunApplied": true, "shortfallCents": 1, "durationSeconds": 1, "quotedPriceCents": 1, "balanceAfterCents": 1, "balanceBeforeCents": 1, "recommendedProduct": "texte"}}

• start_training≈ 793 tokens

  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.

  Paramètres, retour & exemple (1)

  Paramètres

  • jobId · string · requis

  Exemple d'appel

  {"name": "start_training", "arguments": {"jobId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "links": {}, "epochs": "texte", "status": "texte", "upload": "texte", "etaText": "texte", "message": "texte", "artifacts": "texte", "createdAt": "texte", "expiresAt": "texte", "modelName": "texte", "startedAt": "texte"}}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://nicevois.com/api/mcp