Skip to main content
Glama
veniceai

Venice MCP Server

Official
by veniceai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Venice TTS (Speech)

venice_tts

Convert text to speech using cloned voices and emotion tags, with optional wallet or API-key auth. Produces one complete audio result in formats like mp3 or wav.

Instructions

Convert text to speech. Supports cloned voices + emotion tags ([whispers], [sarcastically], etc.). When streaming=true, Venice streams upstream but this MCP tool buffers and returns one complete audio result; it does not emit incremental MCP chunks. Supports x402 wallet auth (no Venice account needed) and API key.

Input Schema

NameRequiredDescriptionDefault
inputYesText to convert to speech (max 4096 chars).
modelNo
speedNo
voiceNoVoice id; see venice://voices.
streamingNoForward Venice's streaming flag. The MCP result is still buffered into one complete audio response, not delivered incrementally.
temperatureNoSampling temperature. Only supported by some TTS models; unsupported models ignore it.
response_formatNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.3.0
    • addedInput schema / properties / streaming
      Added value: +{
+  "description": "Forward Venice's streaming flag. The MCP result is still buffered into one complete audio response, not delivered incrementally.",
+  "type": "boolean"
+}
    • addedInput schema / properties / temperature
      Added value: +{
+  "description": "Sampling temperature. Only supported by some TTS models; unsupported models ignore it.",
+  "maximum": 2,
+  "minimum": 0,
+  "type": "number"
+}
  2. First observedv0.2.0

TDQS

A4.1/5.0
Behavior5/5

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

Annotations only declare a generic mutation/non-idempotent profile with no side-effect detail. The description adds high-value behavioral context beyond annotations: it discloses that streaming=true does NOT emit incremental MCP chunks because the tool buffers the complete audio, and it documents dual auth paths (x402 wallet with no Venice account vs API key). These are exactly the non-obvious traits an agent needs.

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?

Three sentences, front-loaded with the core purpose and then the two highest-value caveats (streaming buffering, auth options). Dense but every sentence earns its place; no filler or tautology.

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?

No output schema exists, so the description should hint at return shape and it does implicitly ('returns one complete audio result'). Combined with the streaming caveat and auth coverage, it is nearly complete for a TTS tool. Minor gap: it never states the default response format or expected output container.

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 coverage is 57%, above the threshold where the schema alone is deemed sufficient, so a baseline of 3 applies. The description reinforces the streaming semantics already noted in the schema and mentions the emotion-tag input syntax, but adds no detail on model, speed, temperature, or response_format beyond what the schema provides.

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 text to speech') and immediately differentiates scope by listing distinctive capabilities (cloned voices, emotion tags). An agent can distinguish this from siblings like venice_asr (the inverse task) and venice_voice_clone 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 Guidelines3/5

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

The description implies usage via capabilities (cloned voices, emotion tags, streaming) but never states when to use this tool versus alternatives such as venice_asr or venice_music_generate, nor any prerequisite conditions. Usage context is left to inference from the capabilities listed.

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

Deploy Server

Other Tools