Local TTS model

rumik-oss 1

Q: Can rumik-oss 1 run locally?

rumik-oss 1 is listed by LocalClaw as a local TTS option. Hardware fit depends on runtime, model size and backend support.

Catalogue summary: 3B multilingual Indic TTS model with 24 kHz output, four named voices, delivery conditioning and inline vocalization tags. The official release includes sharded safetensors, the Mimi codec assets and one-shot plus CLI examples through Transformers remote code; upstream requires an NVIDIA CUDA GPU.

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

GPU recommendedtext-to-speech generation22 languagesCC-BY-NC 4.0

Choose an app

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

Compare speech models

Open model filesRecommended verified starting point Open in UnslothLaunches Unsloth Desktop on this model Open on Hugging FaceFiles, licence and model card Check 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

8.8/10

Catalogue speed

5.8/10

Model size

3B params; 6.76 GB LM shards plus 0.38 GB Mimi codec

Voices

Four named voices: Ira, Aisha, Siya and Zoya

Can rumik-oss 1 run locally?

rumik-oss 1 can generate speech locally for private voice workflows. Use the verified setup options on this page; no terminal command is required to choose the right path.

CC-BY-NC 4.0 license. Review upstream restrictions before commercial use.

Upstream source

multilingualcontrollableemotion

Audio profile

Cat. quality

8.8

Cat. speed

5.8

Audio

7.8

Best fit

rumik-oss 1 is best for multilingual local speech generation.

Hardware: gpu

Model details

Type

Local TTS model

Family

rumik

Latency

high

Formats

pytorchsafetensors

Languages

hi, bn, ta, te, mr, gu, kn, ml, pa, or, as, ur, ne, sa, mai, mni, brx, doi, kok, sat, ks, en

Context

CUDA-only upstream example; description controls cover tone, accent and pace, with inline laugh, chuckle and sigh tags

Install locally

Check runtimeConfirm the backend supports pytorch, safetensors on your machine.

Open recommended setupUse the app and model links above. LocalClaw does not expose a terminal command.

Test locallyRun a short private audio prompt before moving into production workflows.

Good for

text-to-speech generation
GPU recommended local workflows
multilingual, controllable, emotion

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

CompareBrowse all TTS models Local AIBrowse LLM models macOS appGet LocalClaw