Doubao MCP Server

Python client and CLI for Volcengine/ByteDance Doubao seed-tts-2.0 bidirectional streaming TTS.

Local serverstdioPython

What is the Doubao MCP server?

If you already use Doubao, the doubao mcp server is the piece that lets your assistant work with it directly. Python client and CLI for Volcengine/ByteDance Doubao seed-tts-2.0 bidirectional streaming TTS.

What the server does

doubao-speech is the first PyPI package that covers both directions of Volcengine's modern voice stack:

  • Other Python TTS wrappers hit the older SAMI HTTP endpoint (no streaming,
  • No published PyPI package speaks seed-tts-2.0 bidi-stream or the
  • synthesize() / transcribe() for text → speech / speech → text
  • A CLI that drops straight into agent frameworks (Hermes Agent, Dify, LangChain, n8n, …)
  • Strict mypy on every public module
  • 95% unit test coverage, atomic output writes, proper credential redaction

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • Punctuation — Automatic commas, periods, question marks
  • Low — latency streaming**: 200ms chunks by default; tune via --segment-ms
  • TTS — One synthesize call opens a fresh WebSocket and tears it down at
  • STT — Streaming starts returning partial transcripts within ~500 ms
  • v0.2 — connection-reuse daemon (TCP+TLS amortization), streaming
  • v0.3 — LangChain/LlamaIndex/Dify integration recipes
  • v1.0 — API frozen, semver guarantees
  • endpoint — Behaviour
  • bigmodel_async — Bidirectional, optimized; emits only when text changes
  • bigmodel_nostream — Streaming-input; returns after >15 s or the final packet
  • Direction — Input / Output
  • Alias — Language

Credentials and setup notes

Configuration is passed through the environment: HERMES_LOCAL_STT_COMMAND, VOLCENGINE_APP_ID, VOLCENGINE_ACCESS_TOKEN, DOUBAO_APP_ID, DOUBAO_ACCESS_TOKEN. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Installation

The server ships on PyPI as doubao-speech, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

Where it fits

This sits in the AI and media services group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Doubao's toolset — Punctuation, Low, TTS and 11 more — is a fair guide to whether it matches your workflow.

This entry was verified against Doubao's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Worth knowing first

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Doubao.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
PunctuationAutomatic commas, periods, question marks
Lowlatency streaming**: 200ms chunks by default; tune via --segment-ms
TTSOne synthesize call opens a fresh WebSocket and tears it down at
STTStreaming starts returning partial transcripts within **~500 ms**.
v0.2connection-reuse daemon (TCP+TLS amortization), streaming
v0.3LangChain/LlamaIndex/Dify integration recipes.
v1.0API frozen, semver guarantees.
endpointBehaviour
bigmodel_asyncBidirectional, optimized; emits only when text changes
bigmodel_nostreamStreaming-input; returns after >15 s or the final packet
DirectionInput / Output
AliasLanguage
zh-female-reporterzh-CN
zh-male-warmzh-CN

How to install the Doubao MCP server

{
  "mcpServers": {
    "doubao-tts": {
      "command": "uvx",
      "args": ["doubao-speech"],
      "env": {
        "HERMES_LOCAL_STT_COMMAND": "your-value",
        "VOLCENGINE_APP_ID": "your-value",
        "VOLCENGINE_ACCESS_TOKEN": "your-value",
        "DOUBAO_APP_ID": "your-value",
        "DOUBAO_ACCESS_TOKEN": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
HERMES_LOCAL_STT_COMMANDConfiguration value read at startup.Optional
VOLCENGINE_APP_IDConfiguration value read at startup.Optional
VOLCENGINE_ACCESS_TOKENCredential the server authenticates with.Yes
DOUBAO_APP_IDConfiguration value read at startup.Optional
DOUBAO_ACCESS_TOKENCredential the server authenticates with.Yes

Example prompts to try

  • Use Doubao to Punctuation.
  • Use Doubao to Low.
  • Use Doubao to TTS.

Frequently asked questions

It connects Doubao to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (Punctuation, Low, TTS, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Doubao directly.