Source: https://seerepo.com/compare/datawhalechina/hello-agents/vs/huggingface/speech-to-speech
Markdown source: https://seerepo.com/compare/datawhalechina/hello-agents/vs/huggingface/speech-to-speech.md
Description: hello-agents and speech-to-speech share 12 technologies: FastAPI, uvicorn, OpenAI, Hugging Face, anyio, Rich, onnxruntime, torch, transformers, pillow, Pydantic, and jsonschema. Both are written in Python.

# hello-agents vs speech-to-speech

hello-agents and speech-to-speech share 12 technologies: FastAPI, uvicorn, OpenAI, Hugging Face, anyio, Rich, onnxruntime, torch, transformers, pillow, Pydantic, and jsonschema. Both are written in Python.

- [datawhalechina/hello-agents](https://seerepo.com/r/datawhalechina/hello-agents): 📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程
- [huggingface/speech-to-speech](https://seerepo.com/r/huggingface/speech-to-speech): Build voice agents with open-source models

## What they share and what sets them apart

- In common: FastAPI, uvicorn, OpenAI, Hugging Face, anyio, Rich, onnxruntime, torch, transformers, pillow, Pydantic, jsonschema
- Only in hello-agents: aiosqlite, asyncpg, psycopg2-binary, Postgres, chromadb, Redis, SQLite, libsql-client, oracledb, pymilvus, Qdrant, Flask, python, React, react-dom, fastmcp, starlette, AIOHTTP, Streamlit, Vite, Vue, vue-router, react-router-dom, cycler, fonttools, soupsieve, contourpy, ipywidgets, Plotly, Gradio, matplotlib, seaborn, alembic, SQLAlchemy, python-jose, passlib, bcrypt, accelerate, bitsandbytes, camel-ai, MCP, mermaid, peft, safetensors, tavily-python, textblob, tokenizers, hello-agents, agentscope, scikit-learn, sentence-transformers, tiktoken, autogen-agentchat, autogen-ext, datasets, langchain-openai, langdetect, LangGraph, paddlenlp, rank-bm25, spaCy, imaplib2, lxml, markdown, openpyxl, pdfminer.six, pypdf, python-docx, reportlab, xlrd, pdfplumber, feedparser, pymupdf, pypdf2, beautifulsoup4, jinja2, pymupdf4llm, annotated-types, email-validator, kubernetes, OpenTelemetry, opentelemetry-exporter-otlp-proto-grpc, loguru, ant-design-vue, D3, @ant-design/icons-vue, katex, Tailwind CSS, markdown-it, vue-flow, @monaco-editor/loader, Chart.js, vue-chartjs, highlight.js, dompurify, marked, react-markdown, Element, vue-echarts, echarts, @element-plus/icons-vue, Leaflet, @amap/amap-jsapi-loader, html2canvas, jspdf
- Only in speech-to-speech: LiveKit, mlx-audio, librosa, mlx, nltk, faster-qwen3-tts, mlx-lm, torchaudio

## Side by side

| | hello-agents | speech-to-speech |
|---|---|---|
| Size | 227,369 lines written, 1,215 code files | 106,156 lines written, 146 code files |
| Who writes it | 3.3% of its commits signed by AI. With Codex, Claude Code, and Cursor | 3.8% of its commits signed by AI. With Codex, Claude Code, Cursor, and GitHub Copilot |
| Activity | Last push November 11, 2026, 667 commits, 86,829 stars | Last push November 7, 2026, 1,218 commits, 13,664 stars |
| Tests | 103 test files. 6.8% of its code files have a test that imports them | 155 test files. 68.5% 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, hello-agents or speech-to-speech?

hello-agents, with 227,369 lines written; speech-to-speech has 106,156.

The proof: [datawhalechina/hello-agents's code at commit 2a506bc](https://github.com/datawhalechina/hello-agents/tree/2a506bc7e0e3e2235435559b7f2825057ce9a09c)

### Which has more GitHub stars, hello-agents or speech-to-speech?

hello-agents, with 86,829 stars; speech-to-speech has 13,664.

The proof: [datawhalechina/hello-agents on GitHub](https://github.com/datawhalechina/hello-agents)

### Which has more tests, hello-agents or speech-to-speech?

speech-to-speech, with 155 test files; hello-agents has 103.

The proof: [huggingface/speech-to-speech's code at commit 327a8c1](https://github.com/huggingface/speech-to-speech/tree/327a8c190d4126f8f7e06287b1086078835a5a4a)

### Which was updated more recently, hello-agents or speech-to-speech?

hello-agents: its last push was on November 11, 2026, and speech-to-speech's on November 7, 2026.

The proof: [datawhalechina/hello-agents's commits on GitHub](https://github.com/datawhalechina/hello-agents/commits)

### Which has more commits signed by AI, hello-agents or speech-to-speech?

speech-to-speech: an AI signed 3.8% of its commits, with Codex, Claude Code, Cursor, and GitHub Copilot; in hello-agents, 3.3%.

The proof: [the commits each tool signed in huggingface/speech-to-speech](https://seerepo.com/r/huggingface/speech-to-speech/ai)

## Sources

- datawhalechina/hello-agents: Read on November 12, 2026, at commit 2a506bc (https://github.com/datawhalechina/hello-agents/tree/2a506bc7e0e3e2235435559b7f2825057ce9a09c)
- huggingface/speech-to-speech: Read on November 9, 2026, at commit 327a8c1 (https://github.com/huggingface/speech-to-speech/tree/327a8c190d4126f8f7e06287b1086078835a5a4a)

## 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.
