{"id":50235617,"url":"https://github.com/jayuan101/transcript-agent","last_synced_at":"2026-06-07T02:04:18.165Z","repository":{"id":358985076,"uuid":"1242560550","full_name":"jayuan101/transcript-agent","owner":"jayuan101","description":"AI-powered transcription \u0026 interview analysis — 9 STT engines, 8 AI providers, always-on interview scoring","archived":false,"fork":false,"pushed_at":"2026-06-02T00:31:31.000Z","size":661,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-06-02T02:14:40.722Z","etag":null,"topics":["ai","anthropic","audio","gradio","interview","nlp","openai","python","speech-to-text","stt","transcription","whisper"],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/jayuan101.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-05-18T14:36:22.000Z","updated_at":"2026-06-02T00:31:35.000Z","dependencies_parsed_at":"2026-05-20T01:00:31.105Z","dependency_job_id":null,"html_url":"https://github.com/jayuan101/transcript-agent","commit_stats":null,"previous_names":["jayuan101/transcript-agent"],"tags_count":71,"template":false,"template_full_name":null,"purl":"pkg:github/jayuan101/transcript-agent","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jayuan101%2Ftranscript-agent","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jayuan101%2Ftranscript-agent/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jayuan101%2Ftranscript-agent/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jayuan101%2Ftranscript-agent/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jayuan101","download_url":"https://codeload.github.com/jayuan101/transcript-agent/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jayuan101%2Ftranscript-agent/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34006051,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-07T02:00:07.652Z","response_time":124,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai","anthropic","audio","gradio","interview","nlp","openai","python","speech-to-text","stt","transcription","whisper"],"created_at":"2026-05-26T19:04:21.650Z","updated_at":"2026-06-07T02:04:18.131Z","avatar_url":"https://github.com/jayuan101.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"---\ntitle: Transcript Agent\nemoji: 🎙️\ncolorFrom: blue\ncolorTo: indigo\nsdk: docker\napp_port: 7860\npinned: false\n---\n\n# Transcript Agent\n\nAI-powered transcription, interview scoring, and report generation — 9 STT engines × 8 AI providers.\n\n**Bring your own API key.** Billed to your account, nothing stored on the server.\n\n---\n\n## Features\n\n| | |\n|---|---|\n| 🎤 **9 STT engines** | Whisper (local/offline), OpenAI, Groq, Deepgram, AssemblyAI, Google, Azure, ElevenLabs, Rev.ai |\n| 🤖 **8 AI providers** | Claude (Anthropic), OpenAI, Gemini, Groq, Mistral, Together AI, Perplexity, Ollama |\n| 🗣️ **37+ languages** | Auto-detect or select, with regional dialect variants and Indian language support |\n| 🎯 **Interview Mode** | Always-on — scores every question Great / Good / Needs Improvement / Missed, 10-point overall score |\n| 📊 **Deep Analysis** | Deflection rate, advancement likelihood %, coaching guide, prep tips |\n| 📝 **Smart reports** | Summary, key points, action items, speaker profiles, speech analytics |\n| 📁 **History tab** | Every session saved locally — tokens, cost, score, full Q\u0026A replay |\n| 📤 **Exports** | .txt, .docx, .pdf, .srt subtitles, .vtt subtitles, .json |\n| 🌐 **Network monitor** | Always-live download/upload speed, animated bars, session totals |\n| ⏱️ **ETA at every step** | Step tracker + time remaining for Loading, Extracting, Transcribing, and AI Analysis |\n| ⏹️ **Stop \u0026 resume** | Cancel mid-job; re-submit the same file to resume from the saved transcript checkpoint |\n\n---\n\n## Supported formats\n\n| Type | Formats |\n|---|---|\n| Audio | mp3, wav, m4a, flac, ogg, aac, wma |\n| Video | mp4, mov, avi, mkv, webm |\n| Docs | pdf, docx, txt, md, srt, vtt |\n\n---\n\n## Quick start\n\n### Run locally (Python)\n\n```bash\npip install gradio anthropic openai groq pdfplumber fpdf2 python-docx \\\n            deepgram-sdk assemblyai elevenlabs rev_ai \\\n            fastapi uvicorn python-multipart httpx requests\npython app.py\n# Opens http://localhost:7860\n```\n\n### Run with Docker\n\n```bash\ndocker compose up\n# or\ndocker run -p 7860:7860 ghcr.io/jayuan101/transcript-agent\n```\n\n### Windows desktop app\n\n1. Download `TranscriptAgent-win64.zip` + `Install-TranscriptAgent.bat` from [Releases](https://github.com/jayuan101/transcript-agent/releases/latest)\n2. Put both files in the same folder, double-click the `.bat`\n3. It extracts, creates a Desktop shortcut, and launches automatically\n\n### Mac desktop app\n\n1. Download `TranscriptAgent.dmg` from [Releases](https://github.com/jayuan101/transcript-agent/releases/latest)\n2. Open → drag to Applications → double-click to launch\n\n---\n\n## How to use\n\n1. Enter your API key (Claude, OpenAI, Groq, etc.) in the sidebar\n2. Choose your STT engine and AI provider\n3. Upload a file or paste a URL / local path\n4. Click **▶ Analyze**\n\nInterview Mode is always active — every question in the audio is automatically scored and a coaching guide is generated.\n\n---\n\n## Architecture\n\n```\napp.py              — Gradio UI, processing loop, all frontend logic\ntranscript_agent.py — STT dispatch, LLM analysis, report generation\nlauncher.py         — PyInstaller entry point (opens browser on start)\n```\n\n---\n\n## Releases\n\nSee [CHANGELOG.md](CHANGELOG.md) for full version history. Latest: **v1.1.10**\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjayuan101%2Ftranscript-agent","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjayuan101%2Ftranscript-agent","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjayuan101%2Ftranscript-agent/lists"}