Model Detail

higgs-audio-v3-tts-4b is an audio model with 4B parameters released by bosonai. The model is registered under the text-to-speech pipeline tag on Hugging Face, distributed under a other license.

higgs-audio-v3-tts-4b ships with 4B parameters. Total weight footprint is approximately 4.7 GB, which is the relevant figure when planning local-inference VRAM. Distribution is governed by the other license — review the exact terms before commercial deployment.

higgs-audio-v3-tts-4b is best fit for speech recognition, transcription, or speech synthesis depending on the task head. Treat this as a starting matrix rather than a benchmark verdict — the right deployment usually depends on the specific evaluation suite that mirrors your workload.