# pnnbao97/VieNeu-TTS

Vietnamese TTS with instant voice cloning • On-device • Real-time CPU inference • 24kHz audio quality • Chuyển văn bản thành giọng nói tiếng Việt • Text to speech tiếng Việt • TTS tiếng Việt

Repository: https://github.com/pnnbao97/VieNeu-TTS
Canonical: https://ross.abutalabs.com/products/vieneu-tts
Homepage: https://www.vieneu.io
Language: Python
License: Apache-2.0
License Family: permissive
Topics: deep-learning, text-to-speech, on-device-ml, real-time, speech-synthesis, tts, vietnamese-language, vietnamese
Last push: 2026-08-25T11:41:38+00:00

## Health v2 (maintenance only)
Score: 84/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 99, longevity 22
- inputs: {"age_days": 309, "days_push": 8, "days_rel": 8, "gap_med": 0.5, "n_releases_24m": 7}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2427, forks 726 (observed 2026-08-28T04:06:50.824212+00:00)

## What it is
VieNeu-TTS is an on-device Vietnamese text-to-speech library with instant zero-shot voice cloning from short reference clips, supporting bilingual Vietnamese-English code-switching and real-time CPU inference. It offers multiple model versions (up to 48kHz in v3 Turbo), a podcast/conversation multi-speaker mode, and a web UI plus SDK.

## Use cases
- convert Vietnamese text to natural speech
- clone a voice from a short audio clip
- generate multi-speaker podcast or dialogue audio
- run TTS locally on CPU without cloud services
- synthesize speech mixing Vietnamese and English text
- add emotional or non-verbal cues like laughter to speech

## When to choose
- you need high-quality Vietnamese TTS with voice cloning running on-device
- your app requires real-time speech synthesis on CPU
- you need bilingual Vietnamese-English code-switching pronunciation
- you want to generate multi-speaker conversations or podcasts

## When to avoid
- you need TTS for languages other than Vietnamese and English
- you require a managed cloud API rather than self-hosted models
- you need extremely small models for severely constrained embedded devices

## Facets
- artifact type: library
- maturity: active
- function: tts, speech-recognition, machine-learning, deep-learning, audio-processing, llm-inference
- domain: speech-processing, machine-learning
- platform: python, cross-platform
- tags: vietnamese, voice-cloning, on-device, real-time-inference, text-to-speech, bilingual, zero-shot-cloning, natural-language-processing, audio, gpu

## Member repositories
- pnnbao97/VieNeu-TTS (main) score 84

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:50.824212+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:31:36.186716+00:00, confidence not recorded.
  - readme: https://github.com/pnnbao97/VieNeu-TTS (fetched 2026-08-28T04:06:50.824212+00:00, sha 0497d2182a4a)
  - homepage: https://www.vieneu.io (fetched 2026-08-29T10:12:54.495643+00:00, sha dd6ba049c99f)
- Data as of 2026-08-30T08:39:29.467469+00:00.