whisper
by Community
Robust Speech Recognition via Large-Scale Weak Supervision
OSS
whisper
Added 1 June 2026
Overview
Open-source speech-to-text model trained on 680,000 hours of multilingual audio data from the web. Whisper handles various audio conditions, accents, and technical language without requiring fine-tuning. It runs locally via Python and supports 99 languages.
Best for
Best for
Developers building privacy-first or offline-capable voice features with multilingual requirements
Use cases
- Transcribing user audio in applications without cloud API dependency
- Building multilingual voice interfaces and accessibility features
- Processing noisy or accented speech in production systems
Notes
Open-source speech-to-text model trained on 680,000 hours of multilingual audio data from the web. Whisper handles various audio conditions, accents, and technical language without requiring fine-tuning. It runs locally via Python and supports 99 languages.
101,156 stars on GitHub. Last updated 2026-04-15. Licensed MIT.
Use cases
- Transcribing user audio in applications without cloud API dependency
- Building multilingual voice interfaces and accessibility features
- Processing noisy or accented speech in production systems
Pros
- Multilingual support across 99 languages with robust handling of accents and background noise
- Runs entirely on-device, no external API calls required
- Strong community adoption and integration support across frameworks
Cons
- Slower inference than cloud APIs, requires local compute resources
- Model size (up to 3GB for largest variant) impacts deployment footprint
- Accuracy varies by language and audio quality, not optimized for real-time streaming
Indexed from awesome-llmops and enriched against its public facts.
Pros
- Multilingual support across 99 languages with robust handling of accents and background noise
- Runs entirely on-device, no external API calls required
- Strong community adoption and integration support across frameworks
Cons
- Slower inference than cloud APIs, requires local compute resources
- Model size (up to 3GB for largest variant) impacts deployment footprint
- Accuracy varies by language and audio quality, not optimized for real-time streaming
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
gpt-migrate
Community
Easily migrate your codebase from one language or framework to another.
clanker-records/crompton-network
Various
Machine-native listening platform for C.W.A.'s Straight Outta Crompton. Your agent can listen. For real.
eviscerations/whisper-windows-mcp
Various
Windows-native MCP server for local audio transcription — GPU accelerated via Vulkan, works with Claude Desktop
mediar-ai/screenpipe
Various
YC (S26) | AI that knows what you've seen, said, or heard. Records everything you do, say, hear 24/7, local, private, secure
mohitbadwal/ringback
Various
Let your AI agent call your phone and talk to you — MCP servers for live, interruptible voice calls + tiered alerts, using free self-hosted pieces (pjsua2 + whisper.cpp + Linphone)
samson-art/transcriptor-mcp
Various
An MCP server (stdio + HTTP/SSE) that fetches video transcripts/subtitles via yt-dlp, with pagination for large responses. Supports YouTube, Twitter/X, Instagram, TikTok, Twitch, V
transcribe-app/mcp-transcribe
Various
Add transcription tools to your AI-powered assistants.
waxberry-dev/live-translate-mcp
Various
MCP server for local speech translation (EN ↔ 中文) via Whisper + Claude + Piper
AudioGPT
Community
AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head
langchain_yt_tools
Community
Langchain tools to search/extract/transcribe text transcripts of Youtube videos. Some of this has been integrated into LangChain main branch
Marvin
Community
an ambient intelligence library
Off Grid
Community
The Swiss Army Knife of Offline AI. Chat, Speak, and Generate Images - Privacy First, Zero Internet. Download an LLM and use it on your mobile device. No data ever leaves your phon
Pipecat
Community
Open Source framework for voice and multimodal conversational AI
whisper-ctranslate2
Community
Whisper command line client compatible with original OpenAI client based on CTranslate2.
Fireflies
Fireflies.ai
AI meeting assistant. Records, transcribes, summarises, and pipes the output to your stack.
Granola
Granola
AI notepad for meetings. Take your own notes, Granola enhances them after the call with the audio context.
Krisp
Krisp
AI noise cancellation, meeting transcription, and accent translation. The audio layer for the modern call.
Limitless
Various
Go beyond your mind’s limitations: Personalized AI powered by what you’ve seen, said, and heard.
Loopin AI
Various
loopinhq.com
Magnific
Various
The complete platform of creative AI tools for image, video, and audio generation. Create anything from campaigns, product shots to filmmaking. Be Magnific. #magnific
Otter.ai
Various
Otter AI Meeting Agent supports real-time transcription, live chat, automated summaries, insights, and action items.
PyGPT
Various
PyGPT is an open‑source desktop AI assistant for Windows, macOS and Linux. Chat, agents, web search, run Python, TTS/STT, plugins, long‑term memory.
Read AI
Various
Read AI, the fastest growing AI meeting assistant, ever, delivers real-time transcription, smart summaries, and enables AI search and discovery across all your content including
RunThisLLM
Various
Find out exactly what hardware you need to run any local LLM, image, video, or audio AI model. 275+ models with full build specs and performance estimates.
Teleprompter
Various
An on-device AI for your meetings that listens to you and makes charismatic quote suggestions.
Vibe Transcribe
Various
Local-first transcription for audio and video with AI summaries, multilingual support, and privacy-focused processing.
Wispr Flow
Various
Flow makes writing quick and clear with seamless voice dictation. It is the fastest, smartest way to type with your voice.
YouTube Summary with ChatGPT
Various
Use ChatGPT to summarize YouTube videos.
bark
Community
🔊 Text-Prompted Generative Audio Model
CTranslate2
Community
Fast inference engine for Transformer models
simulate-sdk
Community
Enterprise Grade, Voice AI simulation SDK for testing your AI Agents
Affogato
Various
Create AI product video ads in seconds. Generate TikTok, Reels & Shorts that sell — no crew, no editing, just studio-quality ads fast.
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.