Higgs Audio V2 Tokenizer
higgs-audio-v2-tokenizer is an audio tokenizer from Boson AI that converts 24kHz mono audio into discrete codes using a specialized codec. It is designed for use in audio quantization pipelines and can be integrated via the Transformers library or the Moshi framework. The model supports both encoding and decoding operations and is accompanied by evaluation metrics and research papers detailing its acoustic performance.
Open SourceApache-2.0WebCLISelf-hosted
8.3kstars
643forks
1alternative
4features
2025since
Overview
4 featuresHiggs Audio V2 Tokenizer sits in PulseGate's Foundation models & chat category. It focuses on converting raw audio waveforms into discrete tokens suitable for training and running audio generation or understanding models. Higgs Audio V2 Tokenizer is an open-source project aimed at developers. Higgs Audio V2 Tokenizer is open source under the Apache-2.0 license. It ships for the web and the command line, and it can be self-hosted.
It is developed by Boson AI, and it first shipped in 2025. Development happens publicly on GitHub with 8.3k stars and 1 commit in the last 90 days. Key capabilities include Audio Tokenization, Feature Extraction, and quantization. It exposes integrations via a public API.
Summary written by a language model from the project’s public pages.
- Audio Tokenization
- Feature Extraction
- Quantization
- Transformers Compatible
Tags
audio-tokenizerfeature-extractoraudio-quantizationhiggs-model
AI capabilities
Text
Inference: LocalWeights: Open
Built with & integrations
Hosting
AWS
Connectors
API
Runs on
BrowserCLISelf-hosted
Detected from
- AWS
- x-amz-cf-id header · x-amz-cf-pop header · via header
Trust & compliance
License
Apache-2.0
Verified signals
Indexing history
1What PulseGate has recorded for this listing
- Indexed3 Aug · 17:23 UTCbosonai/higgs-audio-v2-tokenizer verified against its public sourceSource: PulseGate · Open
Frequently asked questions about Higgs Audio V2 Tokenizer
- What does Higgs Audio V2 Tokenizer do?
- Higgs Audio V2 Tokenizer focuses on converting raw audio waveforms into discrete tokens suitable for training and running audio generation or understanding models. It is catalogued under Foundation models & chat on PulseGate.
- Who should use Higgs Audio V2 Tokenizer?
- Higgs Audio V2 Tokenizer is an open-source project built for developers.
- Is Higgs Audio V2 Tokenizer free?
- Yes — Higgs Audio V2 Tokenizer is open source under the Apache-2.0 license and free to use.
- What platforms does Higgs Audio V2 Tokenizer run on?
- Higgs Audio V2 Tokenizer runs on the web and the command line. It can also be self-hosted.
- Is Higgs Audio V2 Tokenizer still maintained?
- The GitHub repository shows 1 commit in the last 90 days.
- What projects are similar to Higgs Audio V2 Tokenizer?
- Similar projects tracked by PulseGate include Higgs Audio V2 Tokenizer, Higgs Tts 3 4b, and Higgs Tts 2 3b Base.Higgs Audio V2 TokenizerHiggs Tts 3 4bHiggs Tts 2 3b Base
- Who makes Higgs Audio V2 Tokenizer?
- Higgs Audio V2 Tokenizer is developed by Boson AI.
- How long has Higgs Audio V2 Tokenizer been around?
- Higgs Audio V2 Tokenizer first shipped in 2025.
Similar apps
Closest matches by what these projects do