Gandr MCP vs Voice Bridge
A side-by-side look at the Gandr MCP and Voice Bridge MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Gandr MCP for text-to-speech work as a local process; choose Voice Bridge for text-to-speech as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Gandr MCP when
- You need dedicated capabilities in the Text-to-Speech domain.
- You prefer a local stdio subprocess transport.
- You want tools like
synthesize, list_voices, list_languages.
Choose Voice Bridge when
- You need dedicated capabilities in the Text-to-Speech domain.
- You prefer a local stdio subprocess transport.
- You have the keys it needs:
VOICE_BRIDGE_HOME, ELEVENLABS_API_KEY, VOICE_BRIDGE_MODE, VOICE_BRIDGE_ENGINE, VOICE_BRIDGE_EDGE_VOICE, VOICE_BRIDGE_EDGE_RATE, VOICE_BRIDGE_ELEVENLABS_SPEED, VOICE_BRIDGE_KOKORO_VOICE. - You want tools like
speak, set_engine, get_status.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Text-to-Speech | Text-to-Speech |
| Quality signal | 48/100 · Fair | 49/100 · Fair |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | Not declared | Not declared |
| Pricing | Not declared | Not declared |
| Required env vars | None listed | VOICE_BRIDGE_HOMEELEVENLABS_API_KEYVOICE_BRIDGE_MODEVOICE_BRIDGE_ENGINE |
Tools & capabilities
Gandr MCP tools 4
synthesizeRender text to speech (WAV, base64). Voice, language, sample rate 8000-48000, pitch and pacing dials.list_voicesThe six available voices.list_languagesThe 23 supported languages and their codes.get_usageTokens used by the configured key. One token is one character.
Voice Bridge tools 4
speakSpeak text aloud. Optionally override engine for this call.set_engineSwitch the default TTS engine (`auto`, `edge-tts`, `elevenlabs`, `kokoro`, `say`, `espeak`)get_statusShow current mode, engine, and available engineslist_voicesList available voices. Defaults to current engine if omitted.
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Gandr MCP
{
"mcpServers": {
"gandr-mcp": {
"command": "uvx",
"args": [
"gandr-mcp"
]
}
}
}
Voice Bridge
{
"mcpServers": {
"voice-bridge": {
"command": "npx",
"args": [
"-y",
"ai-voice-bridge"
],
"env": {
"VOICE_BRIDGE_HOME": "YOUR_VOICE_BRIDGE_HOME_HERE",
"ELEVENLABS_API_KEY": "YOUR_ELEVENLABS_API_KEY_HERE",
"VOICE_BRIDGE_MODE": "YOUR_VOICE_BRIDGE_MODE_HERE",
"VOICE_BRIDGE_ENGINE": "YOUR_VOICE_BRIDGE_ENGINE_HERE",
"VOICE_BRIDGE_EDGE_VOICE": "YOUR_VOICE_BRIDGE_EDGE_VOICE_HERE",
"VOICE_BRIDGE_EDGE_RATE": "YOUR_VOICE_BRIDGE_EDGE_RATE_HERE",
"VOICE_BRIDGE_ELEVENLABS_SPEED": "YOUR_VOICE_BRIDGE_ELEVENLABS_SPEED_HERE",
"VOICE_BRIDGE_KOKORO_VOICE": "YOUR_VOICE_BRIDGE_KOKORO_VOICE_HERE"
}
}
}
}
Frequently asked questions
Gandr MCP is categorized under Text-to-Speech and uses a local stdio subprocess. Voice Bridge belongs to Text-to-Speech and uses a local stdio subprocess. Pick Gandr MCP for text-to-speech work and Voice Bridge for text-to-speech.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Gandr MCP has no declared pricing — check the project's own site. Voice Bridge has no declared pricing — check the project's own site. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add gandr-mcp and voice-bridge as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Gandr MCP has a quality signal of 48/100 (Fair) with 0 views, 0 installs and 0 GitHub stars. Voice Bridge has 49/100 (Fair) with 0 views, 0 installs and 0 GitHub stars.