AudioLMGoogle
|
||||||
Related Products
|
||||||
About
AudioLM is a pure audio language model that generates high‑fidelity, long‑term coherent speech and piano music by learning from raw audio alone, without requiring any text transcripts or symbolic representations. It represents audio hierarchically using two types of discrete tokens, semantic tokens extracted from a self‑supervised model to capture phonetic or melodic structure and global context, and acoustic tokens from a neural codec to preserve speaker characteristics and fine waveform details, and chains three Transformer stages to predict first semantic tokens for high‑level structure, then coarse and finally fine acoustic tokens for detailed synthesis. The resulting pipeline allows AudioLM to condition on a few seconds of input audio and produce seamless continuations that retain voice identity, prosody, and recording conditions in speech or melody, harmony, and rhythm in music. Human evaluations show that synthetic continuations are nearly indistinguishable from real recordings.
|
About
MiniMax Audio is an AI-driven audio generation platform that transforms text into realistic speech across 50+ languages, offering over 300 expressive voices, including regional accents like American, Cantonese, Dutch, German, Czech, Japanese, and more, while supporting advanced features such as emotion adjustment, speed, pitch customization, and noise isolation to clean up audio tracks. Users can quickly generate lifelike audio samples via long-text mode, URL input, or voice cloning, capturing a unique voice in as little as 10 seconds, without needing transcription. The underlying technology incorporates cutting-edge AI such as transformer-based TTS models, a learnable speaker encoder, and Flow-VAE architectures, enabling zero- or one-shot voice cloning with high fidelity and expressive control, and it ranks at the top of public voice cloning benchmarks.
|
|||||
Platforms Supported
Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook
|
Platforms Supported
Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook
|
|||||
Audience
Audio researchers and developers needing a solution for creating realistic speech and music continuations directly from raw audio
|
Audience
Creators, developers, and businesses seeking a solution to get text-to-speech voices and efficient voice cloning across global languages for applications
|
|||||
Support
Phone Support
24/7 Live Support
Online
|
Support
Phone Support
24/7 Live Support
Online
|
|||||
API
Offers API
|
API
Offers API
|
|||||
Screenshots and Videos |
Screenshots and Videos |
|||||
Pricing
No information available.
Free Version
Free Trial
|
Pricing
Free
Free Version
Free Trial
|
|||||
Reviews/
|
Reviews/
|
|||||
Training
Documentation
Webinars
Live Online
In Person
|
Training
Documentation
Webinars
Live Online
In Person
|
|||||
Company InformationGoogle
United States
research.google/blog/audiolm-a-language-modeling-approach-to-audio-generation/
|
Company InformationMiniMax Audio
Founded: 2021
Singapore
www.minimax.io/audio
|
|||||
Alternatives |
Alternatives |
|||||
|
|
||||||
|
|
|
|||||
|
|
||||||
Categories |
Categories |
|||||
Integrations
Google Opal
|
||||||
|
|
|