NiceVois

Create an RVC vocal conversion

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. 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.

Input Schema

Name	Required	Description
`modelId`	Yes	A voice id from list_voice_models: one of the user's models, or a licensed library voice (ids starting house_).
`fileName`	Yes	Original WAV, MP3, FLAC, M4A, or OGG vocal filename.
`sizeBytes`	No	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`	No	Pitch shift in semitones, from -24 through 24. Use 0 when no shift was requested.
`wholeSong`	No	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.
`durationSeconds`	Yes	Measured duration of the source audio in seconds. NiceVois uses this to verify that the account can download the result before cloud work.
`acceptsVoiceLibraryTerms`	No	Only after VOICE_LIBRARY_TERMS_REQUIRED, once the user has accepted the linked Voice Library Terms.

Output Schema

Name	Required	Description	Default
`id`	Yes
`error`	No
`stage`	No
`status`	Yes
`upload`	Yes
`outputs`	Yes
`timings`	No
`fileName`	No
`createdAt`	No
`modelName`	No
`transpose`	No
`restoration`	No
`stageMessage`	No
`providerState`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 26, 2026

addedInput schema / properties / acceptsVoiceLibraryTerms

Added value: +{
+  "const": true,
+  "description": "Only after VOICE_LIBRARY_TERMS_REQUIRED, once the user has accepted the linked Voice Library Terms.",
+  "type": "boolean"
+}

changedInput schema / properties / modelId / description

Previous value: -"The id returned by list_voice_models."New value: +"A voice id from list_voice_models: one of the user's models, or a licensed library voice (ids starting house_)."

addedInput schema / properties / wholeSong

Added value: +{
+  "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"
+}

Changed1 schema field changedAug 25, 2026

addedInput schema / properties / sizeBytes

Added value: +{
+  "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"
+}

Changed2 schema fields changedAug 23, 2026

changedInput schema / properties / durationSeconds / description

Previous value: -"Measured duration of the source audio in seconds. NiceVois uses this to reserve cleaned voice-conversion download minutes before cloud work."New value: +"Measured duration of the source audio in seconds. NiceVois uses this to verify that the account can download the result before cloud work."

changedOutput schema / properties / outputs / anyOf

Previous value: -[
-  {
-    "additionalProperties": false,
-    "properties": {
-      "cleaned": {
-        "anyOf": [
-          {
-            "additionalProperties": false,
-            "properties": {
-              "downloadUrl": {
-                "format": "uri",
-                "type": "string"
-              },
-              "listenUrl": {
-                "format": "uri",
-                "type": "string"
-              }
-            },
-            "required": [
-              "listenUrl",
-              "downloadUrl"
-            ],
-            "type": "object"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      },
-      "normal": {
-        "anyOf": [
-          {
-            "additionalProperties": false,
-            "properties": {
-              "downloadUrl": {
-                "format": "uri",
-                "type": "string"
-              },
-              "listenUrl": {
-                "format": "uri",
-                "type": "string"
-              }
-            },
-            "required": [
-              "listenUrl",
-              "downloadUrl"
-            ],
-            "type": "object"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      }
-    },
-    "required": [
-      "normal",
-      "cleaned"
-    ],
-    "type": "object"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "additionalProperties": false,
+    "properties": {
+      "cleaned": {
+        "anyOf": [
+          {
+            "additionalProperties": false,
+            "properties": {
+              "downloadUrl": {
+                "anyOf": [
+                  {
+                    "format": "uri",
+                    "type": "string"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "listenUrl": {
+                "format": "uri",
+                "type": "string"
+              }
+            },
+            "required": [
+              "listenUrl"
+            ],
+            "type": "object"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "normal": {
+        "anyOf": [
+          {
+            "additionalProperties": false,
+            "properties": {
+              "downloadUrl": {
+                "anyOf": [
+                  {
+                    "format": "uri",
+                    "type": "string"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "listenUrl": {
+                "format": "uri",
+                "type": "string"
+              }
+            },
+            "required": [
+              "listenUrl"
+            ],
+            "type": "object"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      }
+    },
+    "required": [
+      "normal",
+      "cleaned"
+    ],
+    "type": "object"
+  },
+  {
+    "type": "null"
+  }
+]

Changed1 schema field changedAug 23, 2026

changedInput schema / properties / durationSeconds / description

Previous value: -"Measured duration of the source audio in seconds. NiceVois uses this to reserve cleaned-output minutes before cloud work."New value: +"Measured duration of the source audio in seconds. NiceVois uses this to reserve cleaned voice-conversion download minutes before cloud work."

Changed2 schema fields changedAug 23, 2026

addedInput schema / properties / durationSeconds

Added value: +{
+  "description": "Measured duration of the source audio in seconds. NiceVois uses this to reserve cleaned-output minutes before cloud work.",
+  "exclusiveMinimum": 0,
+  "maximum": 86400,
+  "type": "number"
+}

changedInput schema / required

Previous value: -[
-  "modelId",
-  "fileName"
-]New value: +[
+  "modelId",
+  "fileName",
+  "durationSeconds"
+]

AddedAug 21, 2026

TDQS

A4.4/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond the annotations by disclosing the quota cost model (one conversion per create, three free, five-minute cap, credit returned on failure), that listening and downloads are free, and that the call returns a private upload instruction rather than a result. These are consequential, non-obvious behaviors for a non-readOnly, openWorld tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the trigger condition and the follow-up call, then the quota rules. It is a single dense paragraph with no filler, though the billing and workflow details packed into one block make it slightly harder to scan than a split would be.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, the description needn't explain return values, and it instead covers the parts the schema cannot: the upload handoff, the follow-up tool, and the quota accounting. Nothing an agent needs to invoke this correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents modelId, transpose, wholeSong, durationSeconds and the terms flag in detail. The description only echoes the 'private voice model' selection and the upload-only-source constraint, adding little parameter-level meaning beyond the structured fields — the correct baseline of 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('convert one vocal recording') plus the precondition ('user has selected a private voice model'), which cleanly separates it from create_audio_job and create_training_job. An agent can distinguish it from every sibling without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit trigger condition ('when the user has selected a private voice model and wants to convert one vocal recording') and a follow-up step ('Upload only the source vocal, then call get_voice_conversion with the same conversion ID'). It does not explicitly rule out the audio-job siblings, so it stops short of full when/when-not coverage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All NiceVois tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?