AllVoiceLab

official

An AI voice toolkit with TTS, voice cloning, and video translation, now available as an MCP server for smarter agent integration.

What can you do with AllVoiceLab MCP?

Clone a voice — Ask the assistant to clone a voice from a short audio sample, preserving pitch, rhythm, and emotion.
Generate expressive TTS — Use text_to_speech to produce lifelike speech in 30+ languages with selectable tones and styles.
Transform a voice — Apply the voice_changer tool to alter a voice without any training or setup.
Isolate vocals — Extract a clean vocal track from any audio file using voice_isolation for editing.
Dub a video — Run multilingual_dubbing to add high-quality translated voiceovers to videos, shows, or shorts.
Extract or remove subtitles — Detect and time-align subtitles with subtitle_extraction, or erase hardcoded text and rebuild backgrounds via subtitle_removal.

Now Live

The next-gen AI engine for voice and video — built to scale your creativity.

Emotional TTS, realistic voice cloning, and multilingual video dubbing, plus more in
one seamless pipeline.

Powerful AI Engines for Next-Level Voice Creation

Start with simple text — get instant access to advanced voice and video tools.

Voice Cloning

Seconds to clone, built to sound real — pitch, rhythm, and emotion preserved

Text-to-Speech (TTS)

Lifelike and expressive AI voices in 30+ languages, tones, and speaking styles

Voice Changer

Flexible and expressive voice transformation — no training, tuning, or setup required

Voice Isolation

Extract clean vocal tracks from any audio — fast, accurate, and ready for editing

Multilingual Dubbing

End-to-end, high-quality multilingual dubbing for global videos, shows, and shorts

Subtitle Extraction

Detect, transcribe, and time-align subtitles from video with >98% accuracy

Subtitle Removal

Remove hardcoded subtitles and reconstruct backgrounds in complex visual scenes

Built With All Voice Lab

From short videos to long-form stories — see what you can build with our AI voice stack.

场景图片

Multilingual Voiceover Generation

Produce expressive voiceovers in 30+ languages — instantly from text,

with emotional tone control and high fidelity.

场景图片

Automated Video Localization

Localize short-form content at scale with auto subtitles, clean visuals,

and multilingual dubbing — all in one flow.

场景图片

One-Click Audiobook Production

From text to fully voiced audio — assign roles, generate voices, and

export in one streamlined workflow.

Developer Hub

[

mcp.so

GitHub