← The evidence ledger
Evidence row 766530
Observed , by probe.mcp/1.
- Kind
- mcp.tools
- About
- endpoint 38e2a607-ebcc-4b4e-88ee-b083e005617e
- Recorded
- Previous row
- #540509
- Body SHA-256
- 58f4f37b12957041632f202080a50eaf3d7d03c67953380d824a61365110eaf1
- Leaf
- 0x5f4a27c7fb7839363b12453529a98f1d896fa7c30c1f609fff3472255bb01d8c
What was observed
{
"count": 19,
"tools": [
{
"description": "Every NiceVois audio tool. With a connected account it runs on that account (a subscriber's unlimited use applies): split_stems, split_lead_backing, remove_noise, remove_reverb, enhance_vocal (Vocal Enhancer, Lite and Unlimited), generate_harmony (upper and lower harmonies from a solo lead vocal). convert_format (audio format converter) is free and also works with no account. Returns an upload URL; then use get_audio_job.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"durationSeconds": {
"description": "Length in seconds if measured; NiceVois measures the file itself after upload.",
"exclusiveMinimum": 0,
"maximum": 86400,
"type": "number"
},
"fileName": {
"description": "The file's name with its extension.",
"maxLength": 180,
"minLength": 1,
"type": "string"
},
"outputFormat": {
"description": "Audio tools: wav (default), flac, mp3 or ogg. convert_format (required): wav, mp3, aac (M4A), flac, ogg, or an advanced format such as wav24, alac or aiff.",
"maxLength": 12,
"type": "string"
},
"sizeBytes": {
"description": "The file's exact size in bytes.",
"exclusiveMinimum": 0,
"maximum": 9007199254740991,
"type": "integer"
},
"tool": {
"enum": [
"split_stems",
"split_lead_backing",
"remove_noise",
"remove_reverb",
"enhance_vocal",
"generate_harmony",
"convert_format"
],
"type": "string"
}
},
"required": [
"tool",
"fileName",
"sizeBytes"
],
"type": "object"
},
"name": "create_audio_job"
},
{
"description": "Split stems, isolate vocals, or remove noise or reverb using the same account allowance as the website. Connect a free account with OAuth or an agent key. No paid subscription is required for the free allowance. Returns an upload URL, then use get_free_audio_job.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"durationSeconds": {
"description": "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.",
"exclusiveMinimum": 0,
"maximum": 86400,
"type": "number"
},
"fileName": {
"description": "The audio file's name with its extension: WAV, MP3, FLAC, M4A or OGG.",
"maxLength": 180,
"minLength": 1,
"type": "string"
},
"outputFormat": {
"default": "wav",
"description": "Format of the files you get back. Use wav unless the user asks for another.",
"enum": [
"wav",
"flac",
"mp3",
"ogg"
],
"type": "string"
},
"sizeBytes": {
"description": "The file's exact size in bytes.",
"exclusiveMinimum": 0,
"maximum": 9007199254740991,
"type": "integer"
},
"tool": {
"description": "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.",
"enum": [
"split_stems",
"split_lead_backing",
"remove_noise",
"remove_reverb"
],
"type": "string"
}
},
"required": [
"tool",
"fileName",
"sizeBytes"
],
"type": "object"
},
"name": "create_free_audio_job"
},
{
"description": "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.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"acceptsStandingAgreement": {
"const": true,
"description": "Set only when the user explicitly accepts the linked standing voice-training agreement after CONSENT_REQUIRED. Omit for accounts that have already accepted.",
"type": "boolean"
},
"contentType": {
"maxLength": 120,
"minLength": 1,
"type": "string"
},
"durationSeconds": {
"exclusiveMinimum": 0,
"type": "number"
},
"epochs": {
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"type": "integer"
},
"fileName": {
"description": "Original WAV, MP3, FLAC, M4A, or OGG filename.",
"maxLength": 255,
"minLength": 1,
"type": "string"
},
"modelName": {
"maxLength": 80,
"minLength": 1,
"type": "string"
},
"sizeBytes": {
"exclusiveMinimum": 0,
"maximum": 9007199254740991,
"type": "integer"
},
"submissionId": {
"maxLength": 80,
"minLength": 8,
"type": "string"
},
"trainingEngine": {
"description": "rvc (default): Standard RVC, portable .pth and .index. nicevois: NiceVois Training (Seed-VC with a finishing pass); returns a complete ZIP, not an RVC index. Requires a training pass or an eligible subscription.",
"enum": [
"rvc",
"nicevois"
],
"type": "string"
}
},
"required": [
"fileName",
"contentType",
"sizeBytes",
"durationSeconds",
"epochs",
"modelName",
"submissionId"
],
"type": "object"
},
"name": "create_training_job"
},
{
"description": "Use this when the user has selected a private voice model and wants to convert one vocal recording. Returns a private upload instruction. Upload only the source vocal, then call get_voice_conversion with the same conversion ID. Creating it counts one of the account's conversions (three free per account, each up to five minutes long; it comes back if the conversion fails); listening and downloads are free.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"acceptsVoiceLibraryTerms": {
"const": true,
"description": "Only after VOICE_LIBRARY_TERMS_REQUIRED, once the user has accepted the linked Voice Library Terms.",
"type": "boolean"
},
"durationSeconds": {
"description": "Measured duration of the source audio in seconds. NiceVois uses this to verify that the account can download the result before cloud work.",
"exclusiveMinimum": 0,
"maximum": 86400,
"type": "number"
},
"fileName": {
"description": "Original WAV, MP3, FLAC, M4A, or OGG vocal filename.",
"maxLength": 255,
"minLength": 1,
"type": "string"
},
"modelId": {
"description": "A voice id from list_voice_models: one of the user's models, or a licensed library voice (ids starting house_).",
"maxLength": 120,
"minLength": 1,
"type": "string"
},
"sizeBytes": {
"description": "Exact byte size of the source audio. Supply it whenever the client can measure the file so interrupted uploads are verifiable and safely resumable.",
"exclusiveMinimum": 0,
"maximum": 9007199254740991,
"type": "integer"
},
"transpose": {
"default": 0,
"description": "Pitch shift in semitones, from -24 through 24. Use 0 when no shift was requested.",
"maximum": 24,
"minimum": -24,
"type": "integer"
},
"wholeSong": {
"description": "true for a finished song with music (for example a Suno track): NiceVois separates it, converts the lead with this voice, keeps the instrumental and backing vocals, and returns the finished cover plus each stem. Leave out for an isolated vocal.",
"type": "boolean"
}
},
"required": [
"modelId",
"fileName",
"durationSeconds"
],
"type": "object"
},
"name": "create_voice_conversion"
},
{
"description": "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.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"fileName": {
"description": "Original .pth or .zip filename.",
"maxLength": 255,
"minLength": 1,
"type": "string"
},
"sizeBytes": {
"exclusiveMinimum": 0,
"maximum": 524288000,
"type": "integer"
}
},
"required": [
"fileName",
"sizeBytes"
],
"type": "object"
},
"name": "create_voice_model_import"
},
{
"description": "Use after get_voice_conversion says the job is complete and the user wants the cleaned or standard output. Downloads are free; the conversion was counted once when it started. If the exact file was downloaded before, ask before retrying and then set confirmRepeat true.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"confirmRepeat": {
"default": false,
"description": "Only true after the user explicitly confirms downloading the same artifact again.",
"type": "boolean"
},
"conversionId": {
"maxLength": 120,
"minLength": 1,
"type": "string"
},
"eventId": {
"pattern": "^[A-Za-z0-9_-]{8,80}$",
"type": "string"
},
"kind": {
"description": "cleaned (recommended) or normal for a vocal conversion; for a whole-song cover, any kind listed in files, for example cover, instrumental or vocal_combined.",
"pattern": "^[a-z][a-z0-9_]{0,39}$",
"type": "string"
}
},
"required": [
"conversionId",
"kind"
],
"type": "object"
},
"name": "download_voice_conversion_output"
},
{
"description": "Returns a short-lived link to one output of a completed audio job. Download it or give it to the user straight away.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"jobId": {
"maxLength": 120,
"minLength": 1,
"type": "string"
},
"output": {
"description": "One of the stems listed by get_audio_job, for example vocal, instrumental, clean, upper or converted.",
"pattern": "^[a-z][a-z0-9_]{0,39}$",
"type": "string"
}
},
"required": [
"jobId",
"output"
],
"type": "object"
},
"name": "get_audio_download"
},
{
"description": "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.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"jobId": {
"description": "The id returned by create_audio_job.",
"maxLength": 120,
"minLength": 1,
"type": "string"
}
},
"required": [
"jobId"
],
"type": "object"
},
"name": "get_audio_job"
},
{
"description": "Use this when a user wants to convert vocals with RVC or compare a normal RVC result with NiceVois cleaned consonants and breaths. Returns the real input formats, model choices, workflow, current free-beta policy, and outputs.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {},
"type": "object"
},
"name": "get_conversion_requirements"
},
{
"description": "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.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"jobId": {
"description": "The id returned by create_free_audio_job.",
"maxLength": 120,
"minLength": 1,
"type": "string"
}
},
"required": [
"jobId"
],
"type": "object"
},
"name": "get_free_audio_job"
},
{
"description": "Call before quoting or creating a training job. Returns the connected account's welcome-credit status, available and reserved balance, balance packs, and a private browser link that keeps checkout on this same agent identity.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {},
"type": "object"
},
"name": "get_training_account"
},
{
"description": "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.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"jobId": {
"maxLength": 120,
"minLength": 1,
"type": "string"
}
},
"required": [
"jobId"
],
"type": "object"
},
"name": "get_training_job"
},
{
"description": "Use this before training an AI voice to confirm NiceVois input formats, duration and epoch limits, consent requirements, outputs, retention, and the exact upload workflow.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {},
"type": "object"
},
"name": "get_training_requirements"
},
{
"description": "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.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"conversionId": {
"maxLength": 120,
"minLength": 1,
"type": "string"
}
},
"required": [
"conversionId"
],
"type": "object"
},
"name": "get_voice_conversion"
},
{
"description": "Use this to see NiceVois's free audio tools (discovery needs no account; processing shares your account allowance): split a song into vocals and instrumental (vocal remover, acapella, karaoke instrumental), split lead vocals from backing vocals, remove background noise, and remove reverb or echo. Returns each tool's id, the accepted formats, and a website link to give the user when you cannot upload their file yourself.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {},
"type": "object"
},
"name": "list_free_audio_tools"
},
{
"description": "Use this to find the authenticated user's recent NiceVois jobs before asking for a job ID they may not know.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {},
"type": "object"
},
"name": "list_training_jobs"
},
{
"description": "Use this when the user wants to convert audio and you need to select one of their private NiceVois-trained or uploaded RVC voices. Do not ask for a model ID before calling this tool.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {},
"type": "object"
},
"name": "list_voice_models"
},
{
"description": "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.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"durationSeconds": {
"exclusiveMinimum": 0,
"type": "number"
},
"epochs": {
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"type": "integer"
},
"trainingEngine": {
"description": "rvc (default): Standard RVC, portable .pth and .index. nicevois: NiceVois Training (Seed-VC with a finishing pass), which chooses its own settings and requires a training pass or an eligible subscription.",
"enum": [
"rvc",
"nicevois"
],
"type": "string"
}
},
"required": [
"durationSeconds",
"epochs"
],
"type": "object"
},
"name": "quote_training"
},
{
"description": "Use this only after the source audio was successfully PUT to the upload URL returned by create_training_job. Starts the private cloud RVC training job.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"jobId": {
"maxLength": 120,
"minLength": 1,
"type": "string"
}
},
"required": [
"jobId"
],
"type": "object"
},
"name": "start_training"
}
]
}What the leaf hashes
{"body":"58f4f37b12957041632f202080a50eaf3d7d03c67953380d824a61365110eaf1","id":766530,"kind":"mcp.tools","method":"probe.mcp/1","observed_us":1793180349448383,"prev":540509,"subject":"38e2a607-ebcc-4b4e-88ee-b083e005617e","subject_kind":"endpoint"}Proof
Fold these into the leaf in order, hashing each sorted pair with keccak256, to reach the root of (231336 rows).
- 0x5f4ad6ac5f62c1db2fc481779eff8b476a942ce46c2ed28aed28569d7be1d710
- 0x11f2e5ac5cac6a4cfbbcf7da979f94e7285166319ac1055b006ed45afea9e66c
- 0x015fbc3eb16460557b42032d4e5ae76c038bac0a0ec4f80ac0a699f1154442a2
- 0x2cd9516e02203b46ebc700a3629e4243d88eb9d1295f68ab7b337fd2e16c133d
- 0xa10609b23ba1a444e7a1a03072c2d7c5cf640e9932570153ef815a5b8ce23b2d
- 0x1f10edcd8742147b3520844c01e3bd42d402faac3108cde258224637f9587066
- 0x7b0dad2d834dafa517ef9b0562e88e22311ad2bd7b076ac6d00d0c728600673b
- 0x7fb76b67acec03f9fcb200584d2053a5ea9ed5ee18832fd7d50c791bc1e65638
- 0xd6e29c037d313c80ad1c3f133fc89487dd984aafef274c34536f41dc19e9fb51
- 0x9da0c3b92950878b3c1291daf1b8199bb14e7304450cbbd185c87e745e7b4888
- 0x60092baa15b626d1471c65ad922fee1e1ef25ffe6ce503b232a651d88ee4db38
- 0xde0ed5a99a265aff1ac56d5267182affd04ee042cab0cdeb668f49339e723a42
- 0xef15c536e795866a8bfb1b8a73e9760d27d138ecef7ee9cc237288f3c6490bbc
- 0x8db2587099a4011758c742fc2aad940742aa47abddf6007f131e0d5ab4a9e92b
- 0xe6054de1f67b1e6f15bcf16d2b6536cf35dd9705fdf6ce59853e79784693ab5f
- 0xa99a40fe210d675bb6ab72d4bb72ab40eb44ac345773c457fbe58e67a47b03df
- 0x7a743a0a09057bae687051274e1d45bf973bd36a1a4ba16a191b5d29e3bdfa2a
- 0xe027395fafb7fc41921c42ca0542524ea22204cbd5908b70b27f3d5fb26f5d0f
- Day root
- 0x2c19037464cc4c493624565f01775d6446fc78eaa118fc6865bfe2bfca9ff78e
- Chained
- 0xd1d7dee8322ceff8f4c8d83aa1fe4a4466825c2af1c97dbde3d35db61234f7be
- Published
- On Arc Testnet, block 69584042: 0x8bae2b1d097834c8b458513862d70d29ee807e98dc2e863b27250131c15b35ae