What is the Volcengine Speech Synthesis MCP Server?

The Volcengine Speech MCP Server gives AI agents like Claude, ChatGPT, and Cursor direct access to Volcengine Speech. The massive 'TikTok Voice' TTS API — generate natural speech with ByteDance's iconic voice models. Powered by the Vinkius AI Gateway — no API keys, no infrastructure, connect in under 2 minutes.

Volcengine Speech MCP Server: see your AI Agent in action

AI Agent→Vinkius→Volcengine Speech Synthesis
You

Vinkius AI Gateway
GDPR·High Security·Kill Switch·Ultra-Low Latency·Plug and Play

Built-in capabilities (7)

create_custom_voice

Requires 10-50 high-quality audio recordings of a single speaker. Training takes 1-3 days. Once complete, use the custom voice_type in synthesize_speech. Create a custom voice model from training audio samples

get_audio_formats

Use MP3 for web delivery, WAV for editing, OGG Opus for efficient streaming, or PCM for raw processing. List supported audio output formats

get_task_status

Returns whether processing, completed, or failed. Check status of an async TTS task

list_voices

Essential for choosing the right voice before synthesis. Includes the famous TikTok voice styles. List all available TTS voice models

synthesize_long_text

Ideal for articles, audiobooks, and lengthy documentation. Use this when your text exceeds the standard 1024 character limit. Synthesize speech from long text (over 1024 characters)

synthesize_speech

Supports multiple languages (Chinese, English, Japanese), various voice styles (female, male, child, trendy, news), and adjustable speed/volume. Returns audio data or URL. Ideal for narration, accessibility, multi-language content, and the iconic TikTok voice effects. Convert text to speech using Volcengine TTS

synthesize_ssml

Use SSML tags like <break>, <emphasis>, <prosody> for natural-sounding output with precise timing and intonation control. Convert SSML (Speech Synthesis Markup Language) to speech

What this connector unlocks

Connect Volcengine Speech Synthesis (ByteDance's TTS platform) to any AI agent and generate stunning natural speech — including the iconic TikTok voices — through natural conversation.

What you can do

  • Text-to-Speech — Convert any text to natural-sounding speech
  • TikTok Voices — Use the exact voice models behind TikTok's viral TTS effects
  • Multi-Language — Synthesize in Chinese, English, Japanese, and more
  • SSML Support — Fine-grained control with pauses, emphasis, and prosody
  • Long-Form Audio — Synthesize articles, audiobooks, and lengthy documents
  • Custom Voices — Train personalized voice models from audio samples
  • Speed/Volume Control — Adjust speech rate and volume dynamically

How it works

1. Subscribe to this server 2. Enter your Volcengine Access Key and Secret Key 3. Start generating speech from Claude, Cursor, or any MCP client

Who is this for?

  • Content Creators — Generate voiceovers for videos, reels, and TikToks
  • Accessibility Teams — Add speech output to apps and websites
  • Audiobook Producers — Convert long-form text to natural narration
  • Developers — Integrate TikTok-quality TTS into applications

Frequently asked questions

Give your AI agents the power of Volcengine Speech

Access Volcengine Speech and 2,500+ MCP servers — ready for your agents to use, right now. No glue code. No custom integrations. Just plug Vinkius AI Gateway and let your agents work.