starccy

starccy / doubaoime-asr

Public

豆包输入法语音识别的非官方 Python 客户端

211
96
69% credibility
Found Feb 05, 2026 at 137 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

A Python library providing unofficial client access to the speech-to-text recognition service of the Doubao input method app.

How It Works

1
🔍 Discover free speech recognition

You hear about a handy tool that turns spoken words in audio files into written text using a popular app's voice service.

2
💻 Set up on your computer

You easily add the tool to your Python environment, and it automatically creates a secure identity to connect to the service.

3
🎤 Prepare your audio

You pick an audio recording from your files or start speaking into your microphone for live use.

4
✨ Start the magic

You run a simple command with your audio, and the tool listens closely to convert speech to text in real time.

5
Choose your style
📁
File mode

Upload a whole recording and get the full text back fast.

🎙️
Live mode

Speak continuously and see words appear as you talk.

✅ Enjoy perfect transcripts

You receive accurate written text from your voice, ready to read, copy, or use anywhere.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 137 to 211 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is doubaoime-asr?

This Python package gives developers unofficial access to Doubao IME's speech-to-text ASR service via a clean async API. Drop in an audio file or mic stream, and it handles transcription, streaming results with interim/final outputs, and real-time processing—perfect for turning voice into text without official SDKs. Install via python github install with `pip install git+https://github.com/starccy/doubaoime-asr.git`, but grab libopus first for audio encoding.

Why is it gaining traction?

It skips API keys or paid tiers by auto-registering virtual devices and managing WebSocket protobuf comms, delivering solid Chinese ASR accuracy fast. Standout hooks include realtime mic support, punctuation toggles, and callbacks for partial results—devs love the zero-config python github package flow over clunky alternatives. At 173 stars, it's popping in python github trending asr projects for quick prototypes.

Who should use this?

Python devs building voice apps, like transcription tools or chatbots needing doubaoime ASR integration. Ideal for ML hobbyists testing speech models or backend folks piping audio from Telegram bots into real-time text. Skip if you need enterprise stability—it's for experimenters eyeing python github api for audio hacks.

Verdict

Grab it for doubaoime asr experiments if unofficial APIs fit your risk tolerance; the 0.7% credibility score flags protocol fragility, but solid README and examples make it dev-ready despite modest 173 stars and no tests. Prototype now, migrate later.

(187 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.