LocalClaw/TTS/Luciole 8B Audio 1.0
Local audio-language model

Luciole 8B Audio 1.0

Catalogue summary: Apache-licensed French and English audio-language model for local ASR, speech translation, audio QA, sound captioning and language recognition. The release ships a 17.38 GB safetensors checkpoint and official NeMo SpeechLM plus vLLM setup notes, with CUDA inference examples for supplied recordings.

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

GPU recommendedspeech-to-speech translation and dubbing2 languagesApache 2.0
Choose an app

Start with the recommended app, or choose another supported option.

Compare speech models
Open model filesModel weights and official local setupOpen in UnslothLaunches Unsloth Desktop on this modelOpen 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
9.1/10
Catalogue speed
6.7/10
Model size
17.38 GB safetensors; 24GB+ GPU class is the practical floor for BF16 local inference
Voices
N/A (audio-language model: outputs text answers, transcripts or translations)

Can Luciole 8B Audio 1.0 run locally?

Luciole 8B Audio 1.0 can run locally for speech-to-speech translation and dubbing over supplied recordings. 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
audio-languagespeech-translationmultilinguallong-formcontrollable

Audio profile

Cat. quality
9.1
Cat. speed
6.7
Audio
8.3

Best fit

Luciole 8B Audio 1.0 is best for local speech translation, dubbing and voice-conditioned multilingual audio workflows.

Hardware: gpu

Model details

Type
Local audio-language model
Family
luciole
Latency
medium
Formats
nemovllmsafetensors
Languages
fr, en
Context
8B Luciole speech-language model, fr/en focus, Parakeet-TDT-0.6B-v3 audio encoder, official NeMo SALM and vLLM plugin paths; model card warns dedicated ASR/AST models may still win outside its tested languages

Install locally

01
Check runtimeConfirm the backend supports nemo, vllm, 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-speech translation and dubbing
  • GPU recommended local workflows
  • audio-language, speech-translation, multilingual

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

NVIDIA MagpieTTS Multilingual 357M Local TTS model · Q 9 · Speed 8.6 IndexTeam / Bilibili Index-Echo S2ST 2B Local speech translation model · Q 9 · Speed 7.8 Mistral AI Voxtral 4B TTS 2603 Local TTS model · Q 9.5 · Speed 9.1 Zyphra ZONOS2 Local TTS model · Q 9.6 · Speed 8.5 dots-studio Dots TTS MF 2-step Local TTS model · Q 9.4 · Speed 8.7 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 k2-fsa / OmniVoice Team OmniVoice Local TTS model · Q 9.1 · Speed 9
CompareBrowse all TTS models Local AIBrowse LLM models macOS appGet LocalClaw