Source: https://seerepo.com/compare/debpalash/VoiceStudio/vs/modelscope/FunASR
Markdown source: https://seerepo.com/compare/debpalash/VoiceStudio/vs/modelscope/FunASR.md
Description: VoiceStudio and FunASR share 7 technologies: FastAPI, androidx.core:core-ktx, librosa, ModelScope, ONNX, onnxruntime, and torch. Both are written in Python.

# VoiceStudio vs FunASR

VoiceStudio and FunASR share 7 technologies: FastAPI, androidx.core:core-ktx, librosa, ModelScope, ONNX, onnxruntime, and torch. Both are written in Python.

- [debpalash/VoiceStudio](https://seerepo.com/r/debpalash/VoiceStudio): VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.
- [modelscope/FunASR](https://seerepo.com/r/modelscope/FunASR): Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

## What they share and what sets them apart

- In common: FastAPI, androidx.core:core-ktx, librosa, ModelScope, ONNX, onnxruntime, torch
- Only in VoiceStudio: Jetpack Compose, pyarrow, OpenAI, PostHog, lifecycle-runtime-compose, Lightning, androidx.navigation:navigation-compose, objc2-app-kit, React, @tanstack/react-router, Vite, Electron, matplotlib, prompt-toolkit, Rich, global-hotkey, Gradio, x11rb, androidx.compose.material:material-icons-core, SQLAlchemy, alembic, bcrypt, cryptography, conformer, diffusers, openai-whisper, torchvision, x-transformers, torchaudio, transformers, faster-whisper, accelerate, MCP, defusedxml, lxml, qrcode, yt-dlp, imageio-ffmpeg, pillow, com.google.zxing:core, Pydantic, loguru, psutil, log, Tailwind CSS, cn, class-variance-authority, @fontsource-variable/inter, @fontsource/ibm-plex-mono, tailwind-merge, react-hot-toast, sonner, Base UI, Radix UI, tanstack, xyflow, react-window, Lucide, country-flag-icons, html-entities
- Only in FunASR: Flask, uvicorn, activity-compose, lifecycle-runtime-ktx, constraintlayout, Google, material3, ui, ui-graphics, androidx.appcompat:appcompat, funasr-onnx, sentencepiece, beautifulsoup4, markdown, YamlDotNet, Microsoft.Extensions.Logging, openclaw

## Side by side

| | VoiceStudio | FunASR |
|---|---|---|
| Size | 689,005 lines written, 1,641 code files | 278,515 lines written, 1,165 code files |
| Who writes it | 28.3% of its commits signed by AI. With Claude Code, Codex, GitHub Copilot, Cursor, and CodeRabbit | 3.3% of its commits signed by AI. With Codex, Claude Code, and Gemini CLI |
| Activity | Last push November 4, 2026, 4,490 commits, 100,682 stars | Last push November 5, 2026, 4,986 commits, 20,948 stars |
| Tests | 1,909 test files. 68.4% of its code files have a test that imports them | 202 test files. 0.9% of its code files have a test that imports them |

- Size: Lines written by people and agents, without generated ones; code files, without tests.
- Who writes it: A commit counts as AI's when it carries its signature: a Co-Authored-By line, its author name or the merge of its branch.
- Activity: From GitHub and its history, on the day SeeRepo read it.
- Tests: The files that test the code, and the share of code files a test imports.

## Frequently asked questions

### Which is bigger, VoiceStudio or FunASR?

VoiceStudio, with 689,005 lines written; FunASR has 278,515.

The proof: [debpalash/VoiceStudio's code at commit 7a896ed](https://github.com/debpalash/VoiceStudio/tree/7a896ed455e116d734f26437393a92cad090aadb)

### Which has more GitHub stars, VoiceStudio or FunASR?

VoiceStudio, with 100,682 stars; FunASR has 20,948.

The proof: [debpalash/VoiceStudio on GitHub](https://github.com/debpalash/VoiceStudio)

### Which has more tests, VoiceStudio or FunASR?

VoiceStudio, with 1,909 test files; FunASR has 202.

The proof: [debpalash/VoiceStudio's code at commit 7a896ed](https://github.com/debpalash/VoiceStudio/tree/7a896ed455e116d734f26437393a92cad090aadb)

### Which was updated more recently, VoiceStudio or FunASR?

FunASR: its last push was on November 5, 2026, and VoiceStudio's on November 4, 2026.

The proof: [modelscope/FunASR's commits on GitHub](https://github.com/modelscope/FunASR/commits)

### Which has more commits signed by AI, VoiceStudio or FunASR?

VoiceStudio: an AI signed 28.3% of its commits, with Claude Code, Codex, GitHub Copilot, Cursor, and CodeRabbit; in FunASR, 3.3%.

The proof: [the commits each tool signed in debpalash/VoiceStudio](https://seerepo.com/r/debpalash/VoiceStudio/ai)

## Sources

- debpalash/VoiceStudio: Read on November 4, 2026, at commit 7a896ed (https://github.com/debpalash/VoiceStudio/tree/7a896ed455e116d734f26437393a92cad090aadb)
- modelscope/FunASR: Read on November 5, 2026, at commit fd1d4aa (https://github.com/modelscope/FunASR/tree/fd1d4aa655effca86dc03b70a09db7e4e6409a10)

## What is your repo built with?

Any public repo, with no account: https://seerepo.com/r/owner/repo/built, with the owner and name it has on GitHub.