LocalClaw/TTS/FireRedAudio
Local ASR model

FireRedAudio

Catalogue summary: Apache-licensed 9B general-purpose audio-language model that can listen, understand, reason, speak and edit. The official PyTorch release covers ASR, long-audio understanding, zero-shot TTS, instruct TTS, voice design and semantic/acoustic speech editing with downloadable Hugging Face weights.

Repository editorial metadata; verify comparative claims in the linked upstream material.

GPU recommendedspeech-to-text transcription2 languagesApache 2.0
Choose an app

Start with Recommended. No terminal commands are shown.

Compare speech models
Open model filesRecommended verified starting pointOpen in UnslothLaunches Unsloth Desktop on this modelOpen official projectApplication source and guided setupOpen on Hugging FaceFiles, licence and model cardCheck my machineOptional: verify the fit with your saved hardware

Desktop app links require the app to be installed. If nothing opens, LocalClaw will show app-download and model-file fallbacks.

Catalogue quality
9.5/10
Catalogue speed
6.6/10
Model size
29.7 GB HF repo; CUDA GPU required
Voices
Zero-shot voice cloning, voice design and speech editing

Can FireRedAudio run locally?

FireRedAudio can run locally for offline speech-to-text. Use the verified setup options on this page; no terminal command is required to choose the right path.

Apache 2.0 license. Still verify upstream usage notes before shipping.

Upstream source
cloningmultilingualcontrollableemotionlong-form

Audio profile

Cat. quality
9.5
Cat. speed
6.6
Audio
8.6

Best fit

FireRedAudio is best for offline transcription, speech indexing and local voice pipelines.

Hardware: gpu

Model details

Type
Local ASR model
Family
firered
Latency
medium
Formats
pytorchsafetensors
Languages
zh, en
Context
9B shared backbone, 29.7GB HF weights plus RedAE decoder, Python 3.10, CUDA toolkit and ffmpeg; generation tasks are Chinese/English only while ASR covers broader benchmarks

Install locally

01
Check runtimeConfirm the backend supports pytorch, safetensors on your machine.
02
Open recommended setupUse the app and model links above. LocalClaw does not expose a terminal command.
03
Test locallyRun a short private audio prompt before moving into production workflows.

Good for

  • speech-to-text transcription
  • GPU recommended local workflows
  • cloning, multilingual, controllable

Watch before shipping

  • Validate pronunciation, latency and artifacts with your own voice samples.
  • Review the upstream license and acceptable-use notes.
  • Benchmark on your target CPU, Apple Silicon or GPU setup.

Related TTS and speech models

OpenMOSS / MOSI.AI MOSS-Transcribe-Diarize 0.9B Local ASR model · Q 9.4 · Speed 8.4 OpenMOSS / MOSI.AI MOSS-Audio 4B Instruct Local ASR model · Q 9.2 · Speed 7.7 KRAFTON AI A.X K2 Raon-Speech 21B-A3B Local ASR model · Q 9.4 · Speed 6.4 Zyphra ZONOS2 Local TTS model · Q 9.6 · Speed 8.5 Bilibili IndexTTS 2.5 Local TTS model · Q 9.5 · Speed 8.4 Boson AI Higgs TTS 3 4B Local TTS model · Q 9.7 · Speed 8 OpenBMB VoxCPM2 Local TTS model · Q 9.4 · Speed 8.3 NetEase Youdao Confucius4-TTS Local TTS model · Q 9.4 · Speed 8.2
CompareBrowse all TTS models Local AIBrowse LLM models macOS appGet LocalClaw