Free online audio and video tools

Synthesises speech from text with Microsoft Edge voices, adjustable for rate and pitch.

Generates natural-sounding conversational speech from text with Sesame's CSM-1B model.

Converts text to natural-sounding speech using the StyleTTS 2 model.

Generates music from text prompts using the ACE-Step music generation foundation model.

Transcribes audio files or microphone input with the Whisper large-v3 model.

Turns text into speech with MeloTTS, a multilingual text-to-speech model.

Syncs a speaker's lip movements in a video to a new audio track using latent diffusion.

Creates a short music sample inspired by the mood of an image you provide.

Reads your text aloud as an audio file, with an optional short clip to match the voice style.

Anime-character style Japanese text-to-speech with many speaker voices.

Converts a voice recording to another voice using a VITS-based voice conversion framework.

Converts an ebook into an audiobook, with support for more than 1,100 languages.

Text-to-speech app that clones a voice for the MegaTTS 3 model, so generated speech follows a chosen voice.

Streams live microphone audio through Whisper on the GPU in your browser and prints the words as you speak.

English speech recognition with NVIDIA Parakeet, returning text and timestamps.

Clone a voice and speak text with it in many languages, including English, Chinese, Japanese, German and Spanish.

Removes noise from speech recordings and boosts clarity.

Web UI for the UVR vocal remover models, with Roformer options and a choice of output format.

Transcribes a video with Whisper and adds a short AI-written summary.

Transcribes a recording in the browser and labels which speaker said each segment.

Separates drums, bass, vocals and other parts of a track with Demucs.

Converts voices with RVC models, with source separation and training options, in a browser app.

Translates the speech of a short video (max 60 s) into another language and re-voices it, with optional lip sync.

Generates songs and covers from a style prompt and lyrics.