HomeProjectsArticlesPK BoardAbout
Explore Projects

WhisperKit

Active
GitHub Swift MIT

Description

Apple-platform Whisper.cpp optimized implementation from Argmax. Focused on iOS / macOS local speech recognition (speech-to-text).

Strengths & Limitations

✅ Strengths

  • • Actively maintained, recent updates
  • • High community interest (6.4k stars)
  • • Permissive open-source license (MIT)
  • • Established track record (2 years in production)

Tags

voice-agent speech-recognition apple-platform

Categories

⚡ Agent Tools
Visit GitHub

Related Projects

FunASR

20.1k · Python
Active A+

FunASR is an industrial-grade open-source speech recognition toolkit from Alibaba DAMO Academy, 170x faster than Whisper. Supports 50+ languages, speaker diarization, emotion recognition, and an OpenAI-compatible API with MCP server.

speech-recognitionASRspeaker-diarization +3
  • · Ultra-fast recognition — SenseVoice-Small runs at 170× realtime on GPU and 17× realtime on CPU
  • · Speaker diarization + emotion recognition — Automatically annotate speaker IDs and emotion labels from a single audio clip
  • · Streaming recognition — WebSocket-based real-time streaming ASR for call QA and live captioning use cases
View full details → View on GitHub

LiveKit

20.7k · Go
Active A+

Open source real-time audio/video infrastructure for AI agents. WebRTC transport, agent framework, SIP telephony, and real-time transcription.

webrtcvoice-agentrealtime +2
  • · Scalable distributed WebRTC SFU (Selective Forwarding Unit) architecture
  • · Full-featured client SDKs for JavaScript, Swift, Kotlin, Flutter, Unity, React Native, and Rust
  • · Production-ready with JWT authentication, end-to-end encryption, and SVC codecs (VP9, AV1)
View full details → View on GitHub

Pipecat

15.1k · Python
Active A

Pipecat is an open-source framework for voice and multimodal conversational AI, enabling real-time voice assistants, video bots, and multimodal agents with integrated TTS, STT, and LLM services.

voice-agentmultimodaltts +4
  • · Real-time voice and multimodal conversational AI framework with ultra-low latency
  • · Multi-agent ready: handoff, parallel fan-out, and distributed deployment
  • · Composable pipeline architecture with modular components for complex behavior
View full details → View on GitHub