# About Audo

Audo: pro sound without the studio. Audio and video tools, workflows, and a browser editor for you and your AI assistant: clean up, transcribe, cut, and more.

## What it does

- [Remove noise](https://audo.ai/noise-removal.md) (`remove_noise`): Turns down background noise, hiss, and hum, keeping the speaker's own voice: it filters the recording and adds nothing. Then sets the whole file to a standard loudness (−16 LUFS). Made for voices: it turns down music and other sounds too.
- [Enhance voice](https://audo.ai/audio-enhancer.md) (`enhance_voice`): Rebuilds the voice, for echo, phone calls, and poor recordings: removes echo, noise, and distortion and restores muffled speech, then sets the whole file to a standard loudness (−16 LUFS). Made for voices: music and other sounds are removed too.
- [Split stems](https://audo.ai/vocal-remover.md) (`split_audio`): Separates a song or video into true stereo stems: vocals and instrumental, 4 stems (vocals, drums, bass, and other), or dialogue, background music, and sound effects. Works on video.
- [Transcribe](https://audo.ai/transcribe.md) (`transcribe_audio`): Text with a time for every word, in 60 languages. Labels who speaks when: Speaker 1, Speaker 2, and so on.
- [Align a script](https://audo.ai/text-to-srt.md) (`align_script`): Lines up a script you already have with the audio, word by word.
- [Cut](https://audo.ai/audio-cutter.md) (`cut_audio`): Trims, removes, or keeps parts of a file by time.
- [Remove silence](https://audo.ai/silence-remover.md) (`remove_silence`): Shortens long pauses. You choose how much of each pause to keep.
- [Set loudness](https://audo.ai/volume-booster.md) (`adjust_loudness`): Sets the level for where it's going: podcasts, YouTube, broadcast, or audiobooks.
- [Convert](https://audo.ai/audio-converter.md) (`convert_audio`): Any format to MP3, WAV, M4A, FLAC, OGG, or Opus, including the audio from a video.
- [Join files](https://audo.ai/audio-joiner.md) (`join_audio`): Puts an intro, the episode, and an outro together, in order.
- [Swap a video's audio](https://audo.ai/replace-audio-in-video.md) (`replace_audio`): Puts a new soundtrack on a video. The picture is copied, so it's fast and loses nothing.
- [Media info](https://audo.ai/media-info.md) (`analyze_audio`): Length, format, loudness, peaks, and noise floor, so you can check before and after.
- [Remove filler words](https://audo.ai/remove-filler-words.md) (`remove_fillers`): Cuts um, uh, and words said twice, in the pauses between words, keeping a natural pause. Works on video.
- [Censor audio](https://audo.ai/bleep-censor.md) (`censor_audio`): Bleep or mute swear words, slurs, and any words you list in audio or video, in place, keeping the music under them if you like.
- [Translate audio](https://audo.ai/audio-translator.md) (`translate_transcript`): Translate a recording into text and subtitles, keeping segment times and speakers.
- [Translate subtitles](https://audo.ai/translate-subtitles.md) (`translate_subtitles`): Translate SRT and VTT subtitles into up to five languages, keeping their timing. Review, edit and download each language.
- Find highlights (`find_highlights`): Rank sentence-aligned moments with titles and reasons through the API or your assistant.
- Shorten transcript (`shorten_transcript`): Select useful original speech and export its retimed transcript and cut list.
- [Level speakers](https://audo.ai/audio-leveler.md) (`level_speakers`): Gives each speaker, or each person's track, one steady level so everyone sounds as loud, keeping music and background as they were.
- [Mix tracks](https://audo.ai/mix-audio.md) (`mix_tracks`): Layers up to 20 tracks with their own volume and start, lines up tracks recorded together, and lowers music under speech.
- [Change speed & pitch](https://audo.ai/change-pitch.md) (`change_speed_pitch`): Shifts a song or recording up or down by up to 12 semitones without changing its speed, and changes speed from 0.25x to 4x with or without keeping the pitch (slowed or sped-up versions). Works on video.
- [Find key & BPM](https://audo.ai/key-bpm-finder.md) (`find_key_bpm`): Finds a song's musical key (such as A minor), its Camelot code for DJ mixing, and its tempo in BPM, with how sure it is of each. Always free.
- [Reverse audio](https://audo.ai/reverse-audio.md) (`reverse_audio`): Plays a recording backwards, end to start, for reversed effects, reverse reverb, or hidden messages. A video gives its reversed sound.
- [Mute a video](https://audo.ai/remove-audio-from-video.md) (`mute_video`): Takes the sound out of a video and keeps the picture exactly as it was, copied rather than re-encoded.
- [Convert video](https://audo.ai/mov-to-mp4.md) (`convert_video`): Convert to MP4, WebM, or MOV, with codec and quality choices.
- [Compress video](https://audo.ai/video-compressor.md) (`compress_video`): Choose a file size or quality, limit resolution and frame rate, and optionally mute.
- [Crop video](https://audo.ai/crop-video.md) (`crop_video`): Crop, rotate, and flip video while keeping its sound.
- [Resize video](https://audo.ai/resize-video.md) (`resize_video`): Fit or fill a ratio or exact dimensions, with zoom, position, color, or blur.
- [Reverse video](https://audo.ai/reverse-video.md) (`reverse_video`): Reverse a range or the whole clip, or make a boomerang with sound options.
- [Loop video](https://audo.ai/loop-video.md) (`loop_video`): Repeat a clip or reach a duration, with optional crossfades.
- Grab a frame (`get_frame`): Save a frame by time or frame number as PNG or JPG, at the width you choose.
- [Video to GIF](https://audo.ai/video-to-gif.md) (`video_to_gif`): Make an animated GIF or WebP from a video range, with frame rate, width, repeats, and a size target.
- [Add captions](https://audo.ai/auto-captions.md) (`add_captions`): Add styled captions to a video, with word highlights, colours, placement, and downloadable subtitle files.
- [Audio to video](https://audo.ai/mp3-to-mp4.md) (`audio_to_video`): Turn an MP3 or other recording into an MP4 audio visualizer and audiogram with a moving waveform, title and cover art.
- [Add text and logo](https://audo.ai/add-text-to-video.md) (`add_overlay`): Add titles, labels and a logo to a video, each placed and timed where you want it.
- Plan a reframe (`reframe_plan`): Get an editable crop plan before rendering a video.
- [Reframe video](https://audo.ai/horizontal-to-vertical-video.md) (`reframe_video`): Turns horizontal video vertical (9:16), square, 4:5, or widescreen, following whoever's talking shot by shot, with every layout, crop, and keyframe editable before it's exported.
- [Text to speech](https://audo.ai/text-to-speech.md) (`text_to_speech`): Read a script aloud as an MP3 with Eleven v4 or Gemini 3.8, in the voice you pick, directed with tags or a style.
- [Subtitles to speech](https://audo.ai/srt-to-speech.md) (`speak_subtitles`): Read an SRT or VTT file aloud with Eleven v4 or Gemini 3.8, each line at its own time, as a voiceover or dubbed onto your video.
- [Voice cloning](https://audo.ai/voice-cloning.md) (`clone_voice`): Clone a voice from a short audio or video recording (or pick one of your saved voices) and generate natural MP3 speech across 30+ languages with Fish Drama 3.
- [Voice changer](https://audo.ai/voice-changer.md) (`change_voice`): Change the speaker's voice in an audio or video recording with ElevenLabs or HeyGen while keeping exact timing, pauses, and delivery.
- [Sound effect generator](https://audo.ai/sound-effect-generator.md) (`generate_sound_effect`): Make a sound effect from a description, such as a whoosh, an impact, footsteps, or rain, 0.5 to 30 seconds long, as an MP3 or 48 kHz WAV, looping seamlessly if you like, with ElevenLabs' SFX v3.
- [Voice design](https://audo.ai/voice-design.md) (`design_voice`): Describe a voice in words, hear three new voices made from it, and save the one you like to read any script, with no recording and nobody's real voice.
- [Generate music](https://audo.ai/ai-music-generator.md) (`generate_music`): Compose royalty-free music from a description with Google's Lyria 3.5 and Lyria 3 Clip: instrumental beds, intros, jingles, or songs with your lyrics.
- [Separate sound](https://audo.ai/sound-remover.md) (`separate_sound`): Remove or isolate any specific sound you describe in English, such as dog barking, footsteps, keyboard typing, applause, drums, or acoustic guitar, across audio and video with Meta SAM Audio. Returns both tracks.
- [Voice recorder](https://audo.ai/voice-recorder.md), in the browser: Records from the microphone in the browser, saving as it goes, then opens the take in Audo's editor to trim, cut, clean up, and export as MP3 or WAV.
- [Screen recorder](https://audo.ai/screen-recorder.md), in the browser: Records a screen, window, or browser tab with system sound, microphone, and an optional camera overlay in the browser, then opens it in Audo's editor to trim, clean up, caption, and export as MP4 or MP3.
- [Webcam recorder](https://audo.ai/webcam-recorder.md), in the browser: Records video and sound from a webcam and microphone in the browser, with a mirror view and script notes, then opens it in Audo's editor to trim, clean up, caption, and export as MP4 or MP3.
- [Record computer audio](https://audo.ai/record-computer-audio.md), in the browser: Captures sound playing in a browser tab or on the computer, with an optional microphone mix, saving as it goes, then opens it in Audo's editor to trim and export as MP3 or WAV.
- [Mic test](https://audo.ai/mic-test.md), in the browser: Checks microphone input level and sound quality in the browser, records a short test take to play back, and opens in the editor to clean up background noise or echo.
- [Editor](https://audo.ai/online-editor.md), in the browser: Audo's non-destructive browser editor for video and audio: cut on multitrack lanes or by transcript words, auto-cut filler words, pauses, and retakes (click any cut to restore), toggle Audio enhancer, Remove noise, or Level voices, add captions and 9:16 speaker tracking, and export once. The file stays on the person's device until one of Audo's tools runs.
- [Audio editor](https://audo.ai/audio-editor.md), in the browser: Audo's editor for sound in the browser: cut by the waveform or by the words, turn on Audio enhancer, Remove noise, Level voices, or podcast loudness, with undo and named versions, and export MP3 or WAV. The file stays on the person's device until one of Audo's tools runs.

Each tool does one job on audio, video, or text, and multi-step workflows or Audo's browser editor combine them in one pass.

## Who it's for

- **Creators, podcasters, and teams with recordings to finish.** Clean up noisy interviews, cut filler words and retakes by text, bleep swear words while keeping the music, clone your voice, design a new voice from a description, swap voices with speech-to-speech, generate voiceovers, dub from subtitles, or compose royalty-free music and sound effects, add captions, reframe wide video to 9:16, or finish everything in Audo's browser editor, with nothing to install.
- **People who automate the first pass with an AI assistant.** Ask ChatGPT, Claude, Claude Code, Codex, or Cursor to find and run Audo's tools and multi-step workflows in plain words, then download the result or open it in the browser editor for final tweaks.
- **Developers and workflow builders.** Every tool, saved voice, tool search, and multi-step workflow is also a REST API and MCP server, free to try without an account, then pay-as-you-go with no monthly subscription.

## Who it isn't for

- **Mastering songs.** Remove noise, Remove echo, and Audio enhancer are tuned for spoken voices and turn music down; for songs, Vocal remover and Stem splitter separate vocals, drums, bass, and instruments.
- **Scoring a whole film or game.** AI music generator composes original songs, intros, and instrumental background music from text, and Sound effect generator makes sound effects up to 30 seconds long, but neither scores a whole film or game to picture.
- **Live audio.** Audo works on files, not on calls or streams as they happen.
- **DAW music production or cinema color grading.** Audo composes royalty-free music from text and handles multitrack voice and music lanes, transcript cuts, captions, overlays, and 9:16 speaker reframing in the browser editor, not MIDI instruments, VST plugins, or cinema color grading.

## Prices and limits

- Editing in the browser editor, recording in the browser, and checking loudness or key/BPM are always free; every other tool has a free allowance (up to an hour on everyday tools, 300 characters on voice generation, 3 voice designs, a 30-second music track, or 10-second sound effects), a few times a day, with no sign-up.
- Full files and scripts are pay-as-you-go: you pay once, with no monthly subscription, and your balance never expires.
- Audio and video uploads up to 10 GB and 10 hours (WAV, MP3, M4A, FLAC, OGG, AAC, Opus, MP4, MOV, MKV, WebM, AVI, SRT, VTT), and scripts up to 8,000 characters.
- Account files are deleted after 24 hours (signed-out free runs after 1 hour); saved voices stay in your account until you delete them.
- Sound and video tools work in any language. Transcription (with speaker diarization), subtitle translation, and script alignment work in 60 languages, bleep censoring includes swear-word lists in 7 languages (and custom words in 60), voice cloning speaks 30+ languages, voice changing supports up to 39 languages, text and subtitle-to-speech speak up to 130 languages, and AI music generation sings in the language of your prompt and lyrics.
- Prices for whole files: https://audo.ai/pricing.md

## Works with

- AI assistants: ChatGPT, Claude, Claude Duet, OpenAI Dots, Meta Muse, Grok Bot, Raycast, Claude Code, Codex, Cursor, Gemini CLI, VS Code, Copilot CLI, Antigravity, Zed, and OpenCode, through the MCP server at https://audo.ai/mcp. Setup: https://audo.ai/setup.md
- Your code: the free API needs no key or account, and an API key runs whole files. Docs: https://audo.ai/docs/api.md
- Every tool, for agents: https://audo.ai/llms.txt

## Who makes Audo

Audo is made by Audo AI, the team behind Audo Studio, our one-click audio cleaner. Learn about Audo Studio at https://audo.ai/studio?utm_source=markdown&utm_medium=agent. Audo AI was founded by Michael Nguyen and Matthew Scholefield.

Questions: support@audo.ai

Follow Audo: [X](https://x.com/audoai), [LinkedIn](https://www.linkedin.com/company/audo-ai).