$ loading_
Clone custom voices for AI assistants and generate playable speech inline.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "voice-mcp" yet — see the docs or source repo.
Use voice-mcp to create a cloned voice from my provided voice sample and name it “Brand Support Voice.” Then use it to read a welcome message: “Hello, welcome to our service center.”
A created voice profile plus a playable audio preview of the welcome message.
Call voice-mcp and use an ElevenLabs voice model to convert the following product intro into natural speech, with an inline player: "This app helps teams automatically organize meeting notes and distribute them quickly."
A natural-sounding narrated product intro with directly playable audio output.
Use voice-mcp to generate speech from both DashScope and ElevenLabs with the same text: “Your order has been processed and will be delivered tomorrow,” and provide two playable results so I can compare voice quality and naturalness.
Two playable speech outputs from different services for comparing pronunciation, tone, and overall quality.
Access text-to-speech, speech-to-text, and voice management via ElevenLabs API.
Generate speech, clone voices, transcribe audio, and create sound effects.
Build voice profiles from samples, then rewrite or generate text in that voice.
Convert text and speech with voice listing, TTS, and transcription tools.
Adds speech recognition and text-to-speech for converting audio and text.
Convert text to speech via one interface with local and cloud engines.