Voice, speech and music
Speech to text, text to speech, voice cloning, voice agents and music generation.
voicestudio leads with 82, ahead of whisper.cpp (76) and pipecat (73).46 projects ranked by score. Updated from public GitHub data.
In Best of Vibe Coding
14 projects, ranked by score.
| Rank | Project | Score |
|---|---|---|
| 1 | agent-starter-reactNext.js voice assistant frontend for LiveKit Agents | 48 out of 100 |
| 2 | voice-ui-kitReact components and templates for Pipecat voice agent frontends | 45 out of 100 |
| 3 | agent-starter-nodeNode.js voice AI agent starter for LiveKit Agents with turn detection | 45 out of 100 |
| #4 | agent-starter-pythonPython voice AI agent starter for LiveKit Agents | 44 out of 100 |
| #5 | pipecat-examplesRunnable Pipecat voice agent examples for phone, web and deployment | 41 out of 100 |
| #6 | agent-starter-androidKotlin and Jetpack Compose voice assistant client for LiveKit Agents | 40 out of 100 |
| #7 | agent-starter-swiftSwiftUI voice agent client for iOS, macOS and visionOS on LiveKit | 39 out of 100 |
| #8 | agent-starter-flutterFlutter voice agent client for iOS, Android, macOS and web | 39 out of 100 |
| #9 | agent-starter-react-nativeExpo React Native voice assistant client for LiveKit Agents | 35 out of 100 |
| #10 | examplesPrompt-generated ElevenLabs examples for speech, music and voice agents | 33 out of 100 |
| #11 | agent-starter-embedDeprecated Next.js embed widget for a LiveKit voice agent | 33 out of 100 |
| #12 | openai-realtime-agentsNext.js demo of multi-agent voice flows on the OpenAI Realtime API | 22 out of 100 |
| #13 | openai-realtime-meeting-assistantVoice-operated shared Kanban board using the OpenAI Realtime API | 22 out of 100 |
| #14 | openai-fmNext.js demo app for trying OpenAI text-to-speech models | 16 out of 100 |
In Best of Open-Source AI
32 projects, ranked by score.
| Rank | Project | Score |
|---|---|---|
| 1 | voicestudioDesktop app for voice cloning, dubbing and dictation with local speech models | 82 out of 100 |
| 2 | whisper.cppC/C++ port of OpenAI Whisper for local speech-to-text transcription | 76 out of 100 |
| 3 | pipecatPython framework for real-time voice and multimodal agent pipelines | 73 out of 100 |
| #4 | VoiceboxLocal voice studio for cloning, TTS, dictation and agent speech | 70 out of 100 |
| #5 | buzzOffline desktop app for transcribing and translating audio with Whisper | 67 out of 100 |
| #6 | meetilyDesktop app that records, transcribes and summarizes meetings locally | 66 out of 100 |
| #7 | speechPyTorch toolkit for training and deploying ASR, TTS and speech LLM models | 65 out of 100 |
| #8 | Speech-to-SpeechLocal voice agent pipeline with an OpenAI Realtime-compatible server | 63 out of 100 |
| #9 | funasrSpeech recognition toolkit with VAD, punctuation, speaker labels and streaming | 62 out of 100 |
| #10 | Kokoro-FastAPIOpenAI-compatible text-to-speech server for the Kokoro-82M model | 62 out of 100 |
| #11 | sherpa-onnxOffline speech recognition, TTS, diarization and VAD runtime built on ONNX Runtime | 61 out of 100 |
| #12 | agentsPython framework for realtime voice and multimodal agents on LiveKit WebRTC | 60 out of 100 |
| #13 | Pocket TTSCPU-only text-to-speech model with voice cloning and streaming | 60 out of 100 |
| #14 | IndexTTSZero-shot TTS with emotion, speed and pronunciation control | 59 out of 100 |
| #15 | voxcpm2B-parameter text-to-speech model with voice design and voice cloning | 58 out of 100 |
| #16 | OpenReaderReads EPUB, PDF and DOCX aloud with synced word highlighting | 58 out of 100 |
| #17 | GPT-SoVITSFew-shot voice cloning and TTS with a training web UI | 56 out of 100 |
| #18 | vibevoiceMicrosoft's open speech models for long-form ASR and streaming TTS | 56 out of 100 |
| #19 | F5-TTSFlow-matching TTS and voice cloning with Gradio and CLI | 54 out of 100 |
| #20 | ace-step-1.5Text-to-music model with LM planner, DiT decoder, Gradio UI and REST API | 53 out of 100 |
| #21 | SpeakrSelf-hosted audio transcription with speaker labels, summaries and chat over recordings | 53 out of 100 |
| #22 | faster-whisperPython Whisper speech-to-text library built on CTranslate2 | 52 out of 100 |
| #23 | whisperMultilingual speech recognition and translation model with Python and CLI interfaces | 51 out of 100 |
| #24 | whisperxBatched Whisper transcription with word-level timestamps and speaker diarization | 48 out of 100 |
| #25 | WhisperLiveNear-real-time Whisper transcription server over WebSocket | 47 out of 100 |
| #26 | chatttsText-to-speech model for dialogue, with laughter and pause control | 45 out of 100 |
| #27 | voice-proGradio web app for transcribing, translating and dubbing video with voice cloning | 43 out of 100 |
| #28 | real-time-voice-cloningSV2TTS voice cloning toolbox: speech from a few seconds of reference audio | 41 out of 100 |
| #29 | SpeachesOpenAI-compatible STT and TTS server with faster-whisper, Kokoro and Piper | 39 out of 100 |
| #30 | spleeterMusic source separation library with pretrained TensorFlow stem-splitting models | 38 out of 100 |
| #31 | open-llm-vtuberVoice-chat AI companion with a Live2D avatar and desktop pet mode | 30 out of 100 |
| #32 | paddlespeechSpeech toolkit on PaddlePaddle for ASR, TTS, translation and speaker verification | 30 out of 100 |
A project's field comes from its own description: what it is made for. All fields.