Qwen3-TTS-Tokenizer-12Hz is a specialized tokenizer for the Qwen3-TTS model. It uses a 12.5 Hz, 16-layer multi-codebook design with a lightweight causal ConvNet to achieve extreme bitrate reduction and ultra-low-latency streaming. It supports encoding audio into tokens and decoding them back to speech.
Qwen3 TTS Tokenizer 12Hz is a Voice, TTS & speech product. It focuses on converting audio to discrete tokens for efficient storage, transport, and low-latency streaming TTS. It is built as an open-source project for Speech AI developers. Qwen3 TTS Tokenizer 12Hz is open source under the Apache-2.0 license. It runs on the web, the command line, and API.
It is developed by Qwen, and the product first shipped in 2026. Development happens publicly on GitHub with 12.5k stars. It operates in a well-populated space: PulseGate tracks 7 similar tools. Key capabilities include Audio Tokenization, Low Latency, and multi-codebook.
Latest indexed changes and source events
Qwen/Qwen3-TTS-Tokenizer-12Hz verified by the PulseGate indexer
