Speech and audio tools

Flash firmware onto an ESP32 board and talk to an AI that can answer and control lights or servos.

Hold a shortcut, speak, and have your words typed into whatever app you are using.

Add a local home screen, private browser and push-to-talk voice commands to a rooted webOS TV.

A set of pipelines that turn an AI coding assistant into a video production line: you describe the video you want in plain language and the agent researches the topic, writes a script, gathers or generates footage, cuts a timeline and renders the result.

Handy lets you press a shortcut, speak, and see your words appear in any text field, transcribed on your own computer.

Build image, video, audio and 3D generation workflows by connecting blocks on a graph; for creators who want control, on Windows, Linux or macOS.

VoiceStudio is a desktop app for generating speech in a chosen voice without sending anything to a company: give it a clean reference recording, type your text, and it generates the audio, with separate workspaces for dubbing video and for designing a brand-new voice from a written description instead of a sample.

The Python library that defines how open models are written down, covering text, images, audio, video and combinations of them, for both running a model and training one.

A local voice studio that covers both halves of speech: going out and coming in.

Cut videos and add auto captions, voices and effects on your own computer.

Audionaut is a free desktop audio editor for music, podcasts and multitrack recordings: cut audio into regions, arrange them in per-track playlists, add crossfades and export, without the weight of a full music studio app.

Collect PDFs, videos and web pages, then search, chat and make podcasts from them.

Turn PDFs, Word files, slides, spreadsheets, images and audio into Markdown text that an AI model can read.

YuE2 is a music generation system that writes a song in two visible steps: given lyrics and a style description, it first produces a melody-and-chord plan in ordinary notation, then turns that plan into finished audio with vocals and backing.

Turn recorded speech into transcripts, translated English text, or a spoken-language label.

OpenWhispr lets you press a hotkey, speak, and see your words typed at your cursor, for people who dictate, take notes or transcribe meetings.

Learn to build AI apps through example projects, from reading text in images to chatting with your documents.

Turn a topic or document into slides, quizzes and discussions led by AI teachers.

AutoClip is a desktop app that watches a long video — a podcast, stream or lecture — and automatically finds and cuts the moments worth sharing, using an AI model you connect (you choose the provider in settings).

Audio8 ASR Infinite is a speech-to-text model built for real-time, unlimited-length transcription rather than processing a finished audio file after the fact.

Turn text into multi-speaker speech with voice cloning and continuation controls.

A 740-million-parameter embedding model from Google DeepMind that turns text, code, images, video and audio into vectors in one shared 768-dimensional space.

LTX-2.5 is a 22-billion-parameter open-weights model from Lightricks that generates video and sound together: describe a scene in words, or hand it a photo, and it produces a clip with a soundtrack in one pass, so picture and audio stay in sync.

For developers building voice apps: LFM3-Audio-2B turns speech into text, text into speech, and answers spoken questions in text or voice.

For developers building voice apps: LFM3-Omni-2B answers questions about photos, video and audio, and replies in text, speech or both.

Give it lyrics and a note about the style and it generates a song with vocals and backing.

Send a screenshot, chart or document and get a written explanation, or hand it a bug to fix.

Generate 4–15 second videos with built-in stereo sound from text, images, video or audio, through an online API, web app or desktop app.

Nemotron-3-Diarization is an open-weight model from NVIDIA that does speaker diarization — working out "who spoke when" in a recording — for up to eight speakers.

Transcribe recordings up to an hour long in 40 languages, with speaker labels and timestamps, or translate speech.

Give one model text, images, video or audio, with up to a million tokens of context such as a whole code repository or a long tool log, and get text back for coding and agent work.

MiMo-V2.6-Pro-RL is Xiaomi's flagship model in the MiMo-V2.6 family, reading and generating text, images, video and audio in one model with a 1-million-token context for handling large codebases or long multi-session agent work.

Hum to Song takes a hummed melody (10 to 30 seconds), plus a style line and lyrics you provide, and turns it into a produced song that keeps your original tune and builds a full structure around it.

Live Speaker Diarization is Nvidia's browser demo for figuring out “who spoke when” in audio: start your microphone or upload a short recording, and it labels overlapping speaker turns in near-real time, showing speaker-activity lanes alongside a live transcript.