speech_recognition

Whisper

openai/whisper

Popular

OpenAI's open-weight multilingual speech recognition model; the baseline for open-source transcription.

faster-whisper

SYSTRAN/faster-whisper

Trending (detected automatically)Popular

Whisper reimplemented on CTranslate2: up to 4x faster with lower memory and the same accuracy.

WhisperX

m-bain/whisperX

Trending (detected automatically)

Whisper with word-level timestamps, forced alignment and speaker diarization.

Pipecat

pipecat-ai/pipecat

Trending

Open-source Python framework for real-time voice and multimodal conversational agents.

LiveKit Agents

livekit/agents

Trending

Framework for realtime voice and video AI agents on LiveKit's WebRTC infrastructure.

Kokoro

hexgrad/kokoro

Trending (detected automatically)Rising

Tiny 82M-parameter open-weight TTS model with quality rivaling much larger systems.

Chatterbox

resemble-ai/chatterbox

Trending (detected automatically)Rising

Resemble AI's open-source TTS with zero-shot voice cloning and emotion control.

NVIDIA NeMo

NVIDIA-NeMo/Speech

NVIDIA's speech AI toolkit, home of the Parakeet and Canary ASR models that top open leaderboards.

ElevenLabs

elevenlabs.io

Popular

Leading hosted API for realistic text-to-speech, voice cloning, speech-to-text and voice agents.