1
News Submissions / TSAC: ultra-low bitrate ultra effective audio compressor by Fabrice Bellard
Last post by birdie -TSAC is an audio compression utility reaching very low bitrates such as 5.5 kb/s for mono or 7.5 kb/s for stereo at 44.1 kHz with a good perceptual quality. Hence TSAC compresses a 3.5 minute stereo song to a file of 192 KiB.
An Nvidia GPU is necessary for fast operation. CPU only is also supported but slower.
Technical information
- TSAC is based on a modified version of the Descript Audio Codec extended for stereo and a Transformer model to further increase the compression ratio. Both models are quantized to 8 bits per parameter.
- The transformer model is evaluated in a deterministic and reproducible way. Hence the result does not depend on the exact GPU or CPU model nor on the number of configured threads. This key point ensures that a compressed file can be decompressed using a different hardware or software configuration.
- In order to get reasonable speed, you need an Nvidia Ampere, ADA or Hopper GPU (e.g. RTX 3090, RTX 4090, RTX A6000, A100 or H100) with CUDA >= 12.x. At least 4 GB memory should be available on the GPU. x86 CPUs are supported too but the program is much slower. The CPU must support the AVX2 instruction set in order to run the program. The FFmpeg utility is required to convert input files to raw format.