Speech & audio
Turn speech into text, text into speech, and work with voices, music and sound.
58 projects, highest rated first.
whisper.cpp
A fast, lightweight version of the Whisper speech-to-text model that runs on ordinary computers and phones.
Speech & audioVoiceStudio
A desktop app for cloning voices, dubbing videos, dictation, transcripts and audiobooks on your own computer.
Speech & audioGPT-SoVITS
Clone a voice from a short recording and turn written text into speech that sounds like that person.
Speech & audioVoicebox
A desktop voice studio that clones voices, reads text aloud and lets you dictate, all on your own computer.
Speech & audioWhisper
Turns speech in audio or video into accurate written text, in dozens of languages.
Speech & audioLiveKit Agents
A framework for building AI voice assistants that can talk with people in real time, including over the phone.
Speech & audioPipecat
A Python toolkit for building AI voice assistants that hold natural, real-time spoken conversations.
Speech & audioFish Speech
Open text-to-speech models that create expressive voices, clone voices and voice whole scenes from a script.
Speech & audiosherpa-onnx
Speech recognition, text-to-speech and other voice tools that work offline on phones, computers and small devices.
Speech & audiofaster-whisper
Transcribes speech to text with OpenAI's Whisper model, but faster and using less memory.
Speech & audioNVIDIA NeMo Speech
NVIDIA's toolkit and open models for speech recognition, text-to-speech and voice AI.
Speech & audioSpeechBrain
An open toolkit for building speech AI, such as speech recognition, speaker recognition and noise removal.
Speech & audioFunASR
Turns speech into text, live or from recordings, and can tell speakers apart and add punctuation.
Speech & audioWhisperX
Fast speech-to-text that gives a time for every word and labels who is speaking.
Speech & audiopyVideoTrans
Translates videos into another language automatically, with new subtitles and AI-dubbed voices.
Speech & audioIndexTTS
Reads text aloud in a voice copied from one short audio clip, with control over emotion and speed.
Speech & audioESPnet
A research toolkit for speech AI: transcription, text-to-speech, speech translation and more.
Speech & audioTEN Framework
A toolkit for building AI assistants you can talk to out loud, in real time.
Speech & audioOpenWhispr
A desktop dictation app: press a key, speak, and your words appear as text wherever you type.
Speech & audioVosk
Turns speech into text offline, in more than 20 languages, even on small devices like phones.
Speech & audioPaddleSpeech
A toolkit that turns speech into text, text into speech, and translates spoken English into Chinese.
Speech & audioedge-tts
Turns text into spoken audio files using the voices from Microsoft Edge's read-aloud feature.
Speech & audioFluidVoice
A Mac dictation app that turns your speech into text in any app, working on your computer.
Speech & audioChatTTS
Turns text into natural, chatty-sounding speech in English and Chinese, with laughs and pauses.
Speech & audioMLX-Audio
A code library for speech, transcription and music AI that runs fast on Apple Silicon Macs.
Speech & audioDograh
Build AI voice agents that answer and make phone calls, using a visual drag-and-drop workflow builder.
Speech & audioVibe
A desktop app that turns speech in audio and video into text, on your own device.
Speech & audioSpeech To Speech
A voice assistant you talk to out loud, built from open models that run on your own computer.
Speech & audioYuE2
Turns your lyrics and a style description into a full song with vocals and backing music.
Speech & audioPedalboard
Spotify's Python library for reading, writing and adding studio effects to audio files.
Speech & audioSenseVoice
A speech model that writes out what was said and also detects the language, emotion and sounds like laughter.
Speech & audioArgmax Open-Source SDK (WhisperKit, TTSKit, SpeakerKit)
Code kits that let iPhone and Mac apps transcribe speech, speak text aloud and tell speakers apart, on the device.
Speech & audioWeNet
A speech recognition toolkit that turns recorded speech into text, built for real-world products.
Speech & audioVoxCPM
An open text-to-speech model that reads text aloud in 30 languages and can design or copy voices.
Speech & audioKokoro-FastAPI
Runs the Kokoro text-to-speech voice model as your own service, with an optional web page.
Speech & audioCosyVoice
Reads text aloud in natural-sounding speech in many languages, and can copy a voice from a short sample.
Speech & audioRTranslator
A free Android app that translates spoken conversations in real time, working offline on your phone.
Speech & audioSpeechRecognition
A Python library that turns speech into text using many different engines, online or offline.
Speech & audioWhisperLiveKit
Live speech-to-text you run yourself, with speaker labels and translation as people talk.
Speech & audioMeetily
A meeting assistant that transcribes and summarises your meetings entirely on your own computer.
Speech & audiopyAudioAnalysis
A Python library for analysing sound: classifying audio, finding events and telling speakers apart.
Speech & audioSmartSub
A free desktop app that makes, translates and voices subtitles for your videos.
Speech & audioannyang
A tiny JavaScript library that lets website visitors control a site with spoken commands.
Speech & audioDia
Turns a written script into realistic spoken dialogue between two voices, including laughs and other sounds.
Speech & audioVideoCaptioner
Creates, fixes, translates and adds subtitles to videos, using speech recognition and AI language models.
Speech & audioEmotiVoice
Turns written text into speech in English or Chinese, with many voices and emotions like happy or sad.
Speech & audioSpleeter
Splits a song into separate tracks, such as vocals, drums, bass and piano.
Speech & audioReal-Time Voice Cloning
A research project that turns typed text into speech in a voice learned from a few seconds of audio.
Speech & audioAbogen
Turns e-books, PDFs and text files into audiobooks with matching subtitles.
Speech & audioSilero Models
Ready-made text-to-speech voices in many languages that are simple to use and run on ordinary computers.
Speech & audioAmphion
A research toolkit for making speech, singing, music and sound with AI.
Speech & audioVoice-Pro
A web app for transcribing, translating and dubbing audio and video, including copying voices from short samples.
Speech & audioWhisper Diarization
Transcribes a recording and labels who said each line.
Speech & audioBasic Pitch
Turns a music recording into MIDI notes, working with almost any instrument, even several at once.
Speech & audioASRT
A speech recognition system that turns spoken Chinese into text.
Speech & audioPodcastfy
Turns websites, PDFs, videos and images into podcast-style audio conversations, in many languages.
Speech & audioOrpheus TTS
An open text-to-speech model that aims to sound human, with emotion control and voice cloning.
Speech & audioACE-Step UI
A music-player-style app for making AI songs on your own computer with the ACE-Step model.