FireRedAudio Open-Sourced: One 9B Model That Listens, Reasons, Speaks and Edits Audio
aigclink · x · 2026-08-31
FireRedAudio is a general-purpose audio language model open-sourced by Xiaohongshu's FireRedTeam, built on a shared 9B-parameter LLM with decoupled continuous representations: an Audio Encoder pathway serves understanding while a RedAE-Patch pathway serves speech generation — claimed to be the first public design of its kind.
A single model covers ASR, audio understanding, zero-shot TTS, instruct TTS, semantic/acoustic speech editing, and accurate temporal grounding over recordings up to one hour. Official PyTorch code is available on GitHub (FireRedTeam/FireRedAudio).
Related event: Xiaohongshu Open-Sources FireRedAudio, a 9B Unified Audio-Language Model(2 posts)→
More from Multimodal
- Surreal AI-generated landscape hides "another landscape inside the measurements" — piotrbinkowski · 2026-10-16
- Fan animation made in Blender with Claude Code (Opus 5.5) — Icy-Appointment3583 · 2026-10-16
- Making Blender animations with Opus, Astra and Argon: how you prompt still matters — chongdashu · 2026-10-16
- Tessellation-free geometric queries on displaced surfaces cut caustics variance 10x — ssh4net · 2026-10-16
- Complex multi-link CAD mechanism finally animates, dev celebrates the breakthrough — zetalyrae · 2026-10-16
- OpenMOSS releases MOSS-Image-SFT: Apache 2.0 text-to-image model on Hugging Face — bdsqlsz · 2026-10-16