Skip to main content
Glama
Venice MCP Server

Venice MCP Server

Official
by veniceai

Venice Voice Clone / List

venice_voice_clone

List available TTS voices or clone a voice from an audio sample URL, returning a vv_ handle for use with the matching text-to-speech model.

Instructions

Discover or clone TTS voices. Action 'list' reads live per-model voice metadata from auth-free GET /v1/models?type=tts. Action 'create' requires sample_url, then uploads the sample to POST /v1/audio/voices for the chosen cloning model. Cloned voices come back as a vv_<id> handle; pass it as venice_tts voice together with the same model. Supports x402 wallet auth (no Venice account needed) and API key.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "action": "<action>"
    },
    "name": "venice_voice_clone"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelNoTTS model the cloned voice is paired with (action=create). Defaults to tts-chatterbox-hd.
actionYeslist = fetch live TTS model voice metadata; create requires sample_url
sample_urlNoRequired for action=create. Audio sample as an http(s) URL or an inline base64 data URL; tts-chatterbox-hd accepts MP3/WAV/FLAC/M4A, tts-minimax-speech-02-hd MP3/WAV only. Include a concrete media type in data URLs, e.g. audio/mpeg for MP3 or audio/mp4 for M4A.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.3.1
    • changedInput schema / properties / sample_url / description
      Previous value: -"Required for action=create. Audio sample URL; tts-chatterbox-hd accepts MP3/WAV/FLAC/M4A, tts-minimax-speech-02-hd MP3/WAV only."New value: +"Required for action=create. Audio sample as an http(s) URL or an inline base64 data URL; tts-chatterbox-hd accepts MP3/WAV/FLAC/M4A, tts-minimax-speech-02-hd MP3/WAV only. Include a concrete media type in data URLs, e.g. audio/mpeg for MP3 or audio/mp4 for M4A."
  2. Changed4 schema fields changedv0.3.0
    • changedInput schema / properties / action / description
      Previous value: -"list = show built-in voices, create = clone from sample_url"New value: +"list = fetch live TTS model voice metadata; create requires sample_url"
    • changedInput schema / properties / model / description
      Previous value: -"Voice cloning model. Required for action=create. Examples: tts-chatterbox-hd, tts-minimax-speech-02-hd."New value: +"TTS model the cloned voice is paired with (action=create). Defaults to tts-chatterbox-hd."
    • addedInput schema / properties / model / enum
      Added value: +[
      +  "tts-chatterbox-hd",
      +  "tts-minimax-speech-02-hd"
      +]
    • changedInput schema / properties / sample_url / description
      Previous value: -"Audio sample URL for action=create. WAV/MP3/M4A."New value: +"Required for action=create. Audio sample URL; tts-chatterbox-hd accepts MP3/WAV/FLAC/M4A, tts-minimax-speech-02-hd MP3/WAV only."
  3. First observedv0.2.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations declare openWorld and non-idempotent, but the description adds material context the annotations cannot: list is an auth-free GET, create uploads a sample to a POST endpoint, and the tool accepts either x402 wallet auth or an API key. It also clarifies that the mixed read/write nature is split by action, which reconciles the coarse readOnlyHint=false. It omits cost/rate-limit and repeat-clone behavior for the create path.

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 purpose, then ordered list-then-create, then the downstream handle handoff. Every sentence carries a fact, though the raw endpoint paths (GET /v1/models?type=tts, POST /v1/audio/voices) are somewhat internal detail that could be trimmed for an agent-facing definition.

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

Completeness4/5

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

With no output schema, the description carries the return-value burden: it explains the vv_<id> handle from create and characterizes list output as per-model voice metadata. The list response shape is only loosely described, which is the remaining gap for a two-mode tool.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds semantics the schema lacks: model is the cloning model the voice is bound to and must match at synthesis time, and sample_url is mandatory only for create. This is real added meaning rather than a restatement of the enum descriptions.

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?

The first sentence names a specific verb pair and resource ('Discover or clone TTS voices'), and the following sentences split the two modes by action name and backing endpoint. An agent can distinguish this from venice_tts (synthesis) and venice_list_models (general model listing) without opening the 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?

It clearly conditions each action: 'list' for reading live voice metadata, 'create' when a sample_url is available, and it routes the agent forward by saying the returned handle is passed to venice_tts with the same model. It stops short of explicit when-not guidance (e.g., when to prefer list over venice_list_models, or when cloning is unnecessary).

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