Alternatives and similar repositories for smart-turn

Users that are interested in smart-turn are comparing it to the libraries listed below

• Standard-Intelligence / hertz-dev
  first base model for full-duplex conversational audio
  ☆1,769Updated 11 months ago
• kyutai-labs / unmute
  Make text LLMs listen and speak
  ☆1,028Updated last week
• kyutai-labs / hibiki
  Hibiki is a model for streaming speech translation (also known as simultaneous translation). Unlike offline translation—where one waits f…
  ☆1,343Updated 8 months ago
• aiola-lab / whisper-medusa
  Whisper with Medusa heads
  ☆864Updated 4 months ago
• pipecat-ai / pipecat-flows
  Open source conversation framework for structured Pipecat dialogues
  ☆499Updated last week
• edwko / OuteTTS
  Interface for OuteTTS models.
  ☆1,415Updated 5 months ago
• davidbrowne17 / csm-streaming
  Realtime demo, Streaming and Finetuning code for CSM
  ☆423Updated 3 months ago
• janhq / ichigo
  Local realtime voice AI
  ☆2,386Updated 3 weeks ago
• lifeiteng / OmniSenseVoice
  Omni SenseVoice: High-Speed Speech Recognition with words timestamps 🗣️🎯
  ☆877Updated last week
• sofdog-gh / realtime-transcription-fastrtc
  Real Time Speech Transcription with FastRTC ⚡️and Local Whisper 🤗
  ☆691Updated 5 months ago
• fluxions-ai / vui
  ☆634Updated last month
• tincans-ai / gazelle
  Joint speech-language model - respond directly to audio!
  ☆372Updated last year
• nyrahealth / CrisperWhisper
  Verbatim Automatic Speech Recognition with improved word-level timestamps and filler detection
  ☆879Updated 6 months ago
• zhenye234 / LLaSA_training
  LLaSA: Scaling Train-time and Inference-time Compute for LLaMA-based Speech Synthesis
  ☆637Updated 8 months ago
• hexgrad / misaki
  G2P
  ☆371Updated 4 months ago
• facebookresearch / spiritlm
  Inference code for the paper "Spirit-LM Interleaved Spoken and Written Language Model".
  ☆925Updated last year
• freddyaboulton / orpheus-cpp
  Fast Streaming TTS with Orpheus + WebRTC (with FastRTC)
  ☆346Updated 8 months ago
• asiff00 / On-Device-Speech-to-Speech-Conversational-AI
  This is an on-CPU real-time conversational system for two-way speech communication with AI models, utilizing a continuous streaming archi…
  ☆215Updated 3 weeks ago
• lhl / voicechat2
  Local SRT/LLM/TTS Voicechat
  ☆744Updated last year
• lucasnewman / f5-tts-mlx
  Implementation of F5-TTS in MLX
  ☆603Updated 9 months ago
• isaiahbjork / orpheus-tts-local
  Run Orpheus 3B Locally With LM Studio
  ☆501Updated 8 months ago
• facebookresearch / omnilingual-asr
  Omnilingual ASR Open-Source Multilingual SpeechRecognition for 1600+ Languages
  ☆2,467Updated this week
• shashikg / WhisperS2T
  An Optimized Speech-to-Text Pipeline for the Whisper Model Supporting Multiple Inference Engine
  ☆532Updated last year
• KoljaB / Linguflex
  Command Your World with Voice
  ☆782Updated 6 months ago
• Lex-au / Orpheus-FastAPI
  High-performance Text-to-Speech server with OpenAI-compatible API, 8 voices, emotion tags, and modern web UI. Optimized for RTX GPUs.
  ☆620Updated 5 months ago
• kyutai-labs / delayed-streams-modeling
  Kyutai's Speech-To-Text and Text-To-Speech models based on the Delayed Streams Modeling framework.
  ☆2,652Updated 3 weeks ago
• isaiahbjork / csm-voice-cloning
  Sesame CSM 1B Voice Cloning
  ☆327Updated 9 months ago
• senstella / csm-mlx
  An implementation of the CSM(Conversation Speech Model) for Apple Silicon using MLX.
  ☆388Updated 4 months ago
• pipecat-ai / pipecat-client-web
  Real-Time Voice Inference Web SDK
  ☆292Updated 2 weeks ago
• phildougherty / sesame_csm_openai
  OpenAI compatible TTS for Sesame CSM:1b & dia:1.6b - Voice Cloning from File/YT
  ☆430Updated 2 months ago