vivekuppal/transcribe
Transcribe is a real time transcription, conversation, Language learning platform. It provides live transcripts from microphone and speaker. It generates a suggested conversation response using OpenAI's GPT API. It will read out the responses, simulating a real live conversation in English or another language.
Built on Python with optional GPU acceleration via CUDA, the platform supports multiple speech-to-text backends (offline transcription or paid services like OpenAI Whisper and Deepgram) and pluggable LLM inference engines including OpenAI, Together, Perplexity, and Azure. Streaming LLM responses enable real-time conversation flow, with configuration via YAML overrides for model selection, prompt customization, and response audio synthesis. Security-hardened with GitGuardian secret scanning, Bandit static analysis, and Snyk dependency checks on every commit.
250 stars.
Stars
250
Forks
57
Language
Python
License
MIT
Category
Last pushed
Feb 11, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/vivekuppal/transcribe"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
meizhong986/WhisperJAV
ASR/STT subtitle generator. Uses Qwen3-ASR, local LLM, Whisper, TEN-VAD. Noise-robust for JAV
BryceWG/BiBi-Keyboard
说点啥（BiBi Keyboard）:一个基于 Kotlin 的 Android 平台的 LLM 与 ASR 语音输入法键盘应用 An LLM ASR voice input method...
DevEmperor/Dictate
A powerful Whisper AI keyboard for reliable speech transcription
sindresorhus/awesome-whisper
🔊 Awesome list for Whisper — an open-source AI-powered speech recognition system developed by OpenAI
FireRedTeam/FireRedASR
Open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English,...