TTS Model Fine-Tuning Voice AI Tools

Repositories for fine-tuning and training text-to-speech models on custom datasets, including LoRA and full model adaptation. Does NOT include pre-built TTS services, inference-only implementations, or general voice cloning without model training.

There are 52 tts model fine-tuning tools tracked. The highest-rated is ekwek1/soprano-factory at 48/100 with 212 stars.

Get all 52 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=voice-ai&subcategory=tts-model-finetuning&limit=20"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

# Tool Score Tier
1 ekwek1/soprano-factory

Soprano-Factory: Train your own 2000x realtime text-to-speech model

48
Emerging
2 TuananhCR/Dia-Finetuning-Vietnamese

TTS Dia finetuning for Vietnamese

46
Emerging
3 shhossain/BanglaTTS

BanglaTTS is a text-to-speech (TTS) system for Bangla language that works in...

45
Emerging
4 thinhlpg/vixtts-demo

A Vietnamese Voice Cloning Text-to-Speech Model ✨

44
Emerging
5 dangvansam/viet-tts

VietTTS: An Open-Source Vietnamese Text to Speech

44
Emerging
6 NTT123/vietTTS

Vietnamese Text to Speech library

43
Emerging
7 modelscope/KAN-TTS

KAN-TTS is a speech-synthesis training framework, please try the demos we...

40
Emerging
8 OwenTyme/voice-zero

Collection of samples suitable for use with zero-shot text to speech engines.

39
Emerging
9 phatjkk/SpeakIt_Vietnamese_TTS

Vietnamese Text-to-Speech on Windows Project (zalo-speech)

39
Emerging
10 yrom/finetune-index-tts

IndexTTS Fine-tuning notebooks

38
Emerging
11 mozilla-ai/speech-to-text-finetune

Blueprint by Mozilla.ai for finetuning a Speech-To-Text model in your own language

37
Emerging
12 Degon3399/XTTS_V2

This repository offers a framework for fine-tuning the XTTS_V2 model,...

36
Emerging
13 seanghay/KLEA

An open-source Khmer Word to Speech Model. Just single word not sentence!

36
Emerging
14 Jobix-Ai/Iso-Vox

STT 90% Solved — Isolate specific speakers from multi-speaker "cocktail...

35
Emerging
15 quangvu3/coqui-xtts

Coqui XTTS model with Vietnamese added

34
Emerging
16 mobassir94/comprehensive-bangla-tts

Aiming to achieve ultimate Multilingual TTS pipeline with main focus on...

34
Emerging
17 megaease/easevoice-trainer

EaseVoice Trainer is a simple and user-friendly voice cloning and speech...

32
Emerging
18 Troyanovsky/awesome-TTS-Colab

Collection of awesome TTS and voice cloning models to run with Google Colab

32
Emerging
19 smtiitm/Fastspeech2_MFA

Indic TTS for Indian Languages: This is a project on developing...

32
Emerging
20 LEMAS-Project/LEMAS-TTS

LEMAS‑TTS is a multilingual zero‑shot text‑to‑speech system, supporting 10...

31
Emerging
21 asiff00/Training-TTS

Train and finutune text-to-speech models for Bengali and many other languages!

31
Emerging
22 gokhaneraslan/XTTS_V2-finetuning

Training XTTS V2 and PEFT LORA Text-to-Speech (TTS)

30
Emerging
23 zabir-nabil/bangla-tts

Bangla text to speech, Multilingual (Bangla, English) real-time speech...

30
Emerging
24 veralvx/xtts-finetune

XTTS fine-tuning via CLI

28
Experimental
25 GitHub30/asr-tts-vietnamese

Vietnamese Text-to-Speech API

26
Experimental
26 mrmanna/Nvidia_Nemo_FastPitch_TTS_Example

How to Build a High-Quality Text-to-Speech (TTS) System Locally with Nvidia...

25
Experimental
27 Kyubyong/speaker_adapted_tts

Making a TTS model with 1 minute of speech samples within 10 minutes

25
Experimental
28 The-Data-Dilemma/Medibeng-Orpheus-3b-0.1-ft-Fine-Tuning

Medibeng-Orpheus-3b-0.1-ft- A TTS model for bilingual Bengali-English...

25
Experimental
29 6Morpheus6/IndicF5

High-Quality Text-to-Speech for Indian Languages

24
Experimental
30 Taijul007/VieNeu-TTS

🎤 Generate realistic Vietnamese speech with VieNeu-TTS, an advanced...

23
Experimental
31 pilarOG/unit_selection_tts

Toy example on how to build a unit selection TTS in Spanish

23
Experimental
32 LEMAS-Project/LEMAS-Project

LEMAS: A 150K-Hour Large-scale Extensible Multilingual Audio Suite with...

23
Experimental
33 dalmoon15/styletts2-dataset-toolkit

🎤 Streamline voice cloning with the StyleTTS2 Dataset Toolkit, a...

23
Experimental
34 supevil/SoulX-Singer-Eval

🎤 Evaluate zero-shot Singing Voice Synthesis systems for quality, accuracy,...

22
Experimental
35 Bangla-Language-Processing/Katha-Bangla-TTS

The first Bangla Text To Speech System for Bangladeshi Bangla (Katha)

22
Experimental
36 deuxksy/today-vn-news

베트남 뉴스 자동 생성 파이프라인 (TTS, FFmpeg, Hardware Acceleration)

22
Experimental
37 2tocom/F5-TTS-Vietnamese-Google-Colab

Vietnamese TTS, Chuyển văn bản thành giọng nói tiếng Việt, text to speech...

21
Experimental
38 iconclub/zalo-tts

Zalo Text-To-Speech for python

20
Experimental
39 HoseinAzad/SpeechT5-Non-English-TTS

Fine-tune SpeechT5 for non-English text-to-speech task, implemented in PyTorch.

19
Experimental
40 harshanavkis/Hindi-TTS

Text to Speech system for Hindi language

19
Experimental
41 ducnt18121997/Viet-Transformer-TTS

This is PyTorch Implementation of A Non-Autoregressive Transformer with...

19
Experimental
42 ilya16/isp-tts

A simple TTS model developed for the Speech Synthesis and Voice Cloning...

17
Experimental
43 babadue/seamless-m4t-v2-large-demo

Demonstration features of seamless-m4t-v2-large model

16
Experimental
44 NhanPhamThanh-IT/Vietnamese-Voice-Search-Engine

🔎 Vietnamese Voice Search Engine - Vietnamese news search app with voice...

15
Experimental
45 Salama1429/Text-to-speech_TTS_Model_Training

Training Text to speech model for German Language

15
Experimental
46 HQQHQ/FinetuneSpeechT5-Spanish

This repository hosts the code and resources for fine-tuning a SpeechT5...

15
Experimental
47 leanhtech/TextToSpeech_EN_VN

Đồ Án Text To Speech (Môn Hệ Điều Hành - PTITHCM)

14
Experimental
48 lukaszliniewicz/easy_xtts_trainer

A command line utility to easily finetune XTTS models in a fully automated...

13
Experimental
49 CherokeeLanguage/IMS-Toucan

Cherokee Language TTS

13
Experimental
50 usamireko/StableTTS-Training-Colab

A notebook created for training StableTTS models in Google Colab easily!

12
Experimental
51 gas/pronunza-tts-galego-onnx-colab

Caderno de Colab para síntese de voz (TTS) en galego usando o modelo ONNX de Celtia

12
Experimental
52 NoerNova/IMS-Toucan-Shan

fork version of IMS-Toucan to finetuning for Shan language

10
Experimental

Comparisons in this category