Skip to main content
Glama

DeepSeek TTS

deepseek_tts

Synthesize text into speech with DeepSeek's TTS API, save the audio to a local file, and return the saved path, format, and byte size.

Instructions

Synthesize speech with DeepSeek's TTS API and write the audio to a local file. Returns the saved path, format and byte size.

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": {
      "text": "<text>"
    },
    "name": "deepseek_tts"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesText to synthesize. The API accepts up to 10000 billed characters (Chinese counts as 2) and a 64 KiB request body.
formatNoAudio format: wav (default) or raw pcm (24 kHz, 16-bit, mono).wav
voice_idNoVoice: stella (default, female) or tide (male).stella
output_pathNoWhere to write the audio file. Defaults to ~/.cache/deepseek-tools-mcp/tts-<timestamp>.<format>.
filter_markdownNoStrip Markdown before synthesis. Default true.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior3/5

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

With no annotations supplied, the description carries the full burden and does disclose the important traits that this is a filesystem-writing operation plus the shape of the return (path, format, byte size). It omits what happens when output_path already exists (overwrite vs error), whether the call is billable, and auth requirements, which are notable gaps for a side-effecting tool.

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

Conciseness5/5

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

Two sentences, front-loaded with the operation and followed by the return contract. Every clause earns its place with no redundant restatement of the title.

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?

For a five-parameter tool with full schema coverage but no output schema, the description adequately covers the action and explicitly states the return values, so an agent knows what comes back. The only meaningful omission is overwrite behavior at the destination path and any billing or permission caveats.

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 all five parameters, their enums, defaults, and constraints (10,000 billed characters, 64 KiB body, default cache path) are already documented in the schema. The description adds no parameter meaning beyond that, so the baseline of 3 applies.

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 description names a specific verb and resource ("Synthesize speech with DeepSeek's TTS API") and adds the concrete side effect ("write the audio to a local file"). This makes it immediately distinguishable from the sibling deepseek_asr, which performs the inverse operation, without needing to open either 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?

Usage is strongly implied by the operation itself (convert text to audio and save it), but there is no explicit when-to-use or when-not guidance and no mention of alternatives among the siblings. An agent can infer the context but receives no routing rules.

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