MockingBird

Visit Tool

MockingBird is an open-source audio & music tool that clones voices in 5 seconds to generate arbitrary speech in real-time. It supports Chinese Mandarin and runs on Windows, Linux, and M1 macOS.

Claim this tool

2Views

At a glance

Pricing

Open Source

Free tier

Yes

API

Skill level

Technical

About

What is MockingBird?

MockingBird is an open-source voice cloning tool designed for real-time speech generation. It allows users to clone a voice in approximately 5 seconds and generate arbitrary speech. The tool supports Chinese Mandarin and has been tested with multiple datasets, including aidatatang_200zh, magicdata, and aishell3. It is compatible with Windows, Linux, and even M1 macOS, offering flexibility for various environments. MockingBird leverages PyTorch and provides options for training custom models for encoders, synthesizers, and vocoders, or utilizing community-shared pretrained models. It offers a web server, a toolbox, and a command-line interface for generating voices.

Best used for

Ideal for content creators who need to quickly clone voices for unique character voices, podcasters looking to generate consistent speech for segments, and developers experimenting with real-time voice synthesis. Especially valuable for those working with Chinese Mandarin content or requiring an open-source solution.

Common actions

clone voice

generate speech

synthesize audio

open-sourcedeepfakelow-code/no-codeautomated workflowcollaborationworkflowsgithub copilot"AI Agents"face swapping

Capabilities

Key features

Clone voice in 5 seconds
Real-time speech generation
Chinese Mandarin support
Custom model training
Web server interface
Command-line interface

Target Audience

content creatorpodcaster

Integrations

Not yet documented

Pricing & Plans

Open Source

Free

FAQs

What datasets does MockingBird support for Chinese Mandarin?

MockingBird supports and has been tested with several Chinese Mandarin datasets, including aidatatang_200zh, magicdata, aishell3, and data_aishell. Users can specify these datasets during the preprocessing and training phases for custom models.

Can MockingBird run on Apple M1 Macs?

Yes, MockingBird can run on M1 Macs, but it requires a workaround involving a Rosetta Terminal and specific installation steps for PyQt5, pyworld, and ctc-segmentation. This ensures compatibility with the x86 architecture required by some dependencies.

How can I reduce VRAM usage when training models with MockingBird?

To reduce VRAM usage during training, you can adjust the `batch_size` parameter in the `synthesizer/hparams.py` and `vocoder/wavernn/hparams.py` files. Lowering these values, for example from 12 to 8 or 100 to 6, can help manage memory consumption.

Trending

Subcategories trending in Content & Design

Image Generation AI Writing Assistants Video Generation Photo Editing Graphic Design Video Editing

Trending

Also listed in

This tool also appears in

Coding & Development › Open Source & Models AI Agents & Automation › Voice Agents

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce