10 alternatives to GPT-SoVITS
rvc-boss/gpt-sovits — 1 min voice data can also be used to train a good TTS model! (few shot voice cloning) (64,570 stars, MIT, integration, infra, ai).
These are the closest projects in the JustClaw-It index that we serve licence-cleared code from, ranked by relevance and by our code-quality score (1–10, the mean over each repo's graded components: completeness, code quality, deployability, reusability, strategic value). JustClaw-It also serves 163 licence-cleared components from rvc-boss/gpt-sovits itself.
| # | Repo | Score | Licence | Stars |
|---|---|---|---|---|
| 1 | openbmb/voxcpm | 4.7 | Apache-2.0 | 41,796 |
| 2 | pndurette/gtts | 7.6 | MIT | 2,638 |
| 3 | openmoss/moss-tts-nano | 6.8 | Apache-2.0 | 4,559 |
| 4 | devnen/kitten-tts-server | 6.9 | MIT | 281 |
| 5 | devnen/dia-tts-server | 6.9 | MIT | 355 |
| 6 | rvc-project/retrieval-based-voice-conversion-webui | 6.6 | MIT | 38,845 |
| 7 | kittenml/kittentts | 6.7 | Apache-2.0 | 16,493 |
| 8 | leemysw/yovoice | 5.0 | Apache-2.0 | 2,086 |
| 9 | minimax-ai/minimax-mcp | 6.3 | MIT | 1,596 |
| 10 | devnen/chatterbox-tts-server | 6.9 | MIT | 1,483 |
The alternatives in detail
-
VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning
-
Python library and CLI tool to interface with Google Translate's text-to-speech APIscore 7.6/10 · MIT permissive · 2,638 stars · 12 components · search them
-
A 100M-parameter multilingual TTS model for real-time CPU inference, voice cloning, and 48 kHz stereo generationscore 6.8/10 · Apache-2.0 permissive · 4,559 stars · 18 components · search them
-
Self-host the ultra-lightweight Kitten TTS model with this enhanced API server with an intuitive Web UI, large text processing for audiobooks, and GPU acceleration.score 6.9/10 · MIT permissive · 281 stars · 6 components · search them
-
Self-host the powerful Dia TTS model. This server offers a user-friendly Web UI, flexible API endpoints (incl. OpenAI compatible), support for SafeTensors/BF16, voice cloning, dialogue generation, and GPU/CPU execution.score 6.9/10 · MIT permissive · 355 stars · 12 components · search them
-
Easily train a good VC model with voice data <= 10 mins!score 6.6/10 · MIT permissive · 38,845 stars · 120 components · search them
-
Open-source State-of-the-art TTS model which runs on a CPU 😻score 6.7/10 · Apache-2.0 permissive · 16,493 stars · 35 components · search them
-
Open-source local AI audio & music studio for macOS & Windows. TTS, voice cloning, songs with lyrics, and multi-track scores — 100% offline, zero API fees.score 5.0/10 · Apache-2.0 permissive · 2,086 stars · 365 components · search them
-
Official MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.score 6.3/10 · MIT permissive · 1,596 stars · 8 components · search them
-
Self-host the powerful Chatterbox TTS model. This server offers a user-friendly Web UI, flexible API endpoints (incl. OpenAI compatible), predefined voices, voice cloning, and large audiobook-scale text processing. Runsscore 6.9/10 · MIT permissive · 1,483 stars · 9 components · search them
Licence data: JustClaw-It's per-repo licence policy. Is GPT-SoVITS still maintained? Check it. Licence details: licence checker. Ranking data from 2026-11-09T05:08:50Z.
Want code like GPT-SoVITS without the licence risk? JustClaw-It is an MCP server with 4,918,000+ licence-cleared, scored code components. Search is free; every result carries its licence and attribution.
Remote MCP endpoint: https://justclaw.it.com/mcp (API key auth). Works with Claude Code, Cursor,
Codex, Windsurf and other MCP clients. A one-line CLI installer (@justclaw-it/cli) is coming.