Audo docs
Audo runs 45 audio and video tools and multi-step workflows for people and agents. People use the pages and browser editor on this site. Agents use the MCP server (with find_tools for plain-language tool discovery), or call the API with curl (POST /api/v1/tools/find, /api/try/<tool>, and /api/v1). Every way in shares the same tools, free tier, and pay-as-you-go prices (pay once from $5, with no monthly subscription and credits that never expire).
Ways in
| Way | Best for | Account |
|---|---|---|
| MCP server | ChatGPT, Claude, Cowork, Claude Code, Codex, Cursor, Gemini CLI, and VS Code. Setup for each | Sign in. The same free tier, then credits |
| Free API | Any agent or script, with one curl request | None for the first part of each file, a few times a day. Add an API key for whole files |
| REST API | Scripts and servers that manage files and jobs | An API key |
There's no command-line tool to install: agents that have a computer use curl, and assistants use MCP.
Tools
| Tool | MCP name | Free API | Price | Free |
|---|---|---|---|---|
| Remove noise | remove_noise | /api/try/remove-noise | $0.05/min | First minute, 3 a day |
| Enhance voice | enhance_voice | /api/try/enhance-voice | $0.05/min | First minute, 3 a day |
| Split stems | split_audio | /api/try/split-stems | $0.08/min | First 45 seconds, 3 a day |
| Transcribe | transcribe_audio | /api/try/transcribe | $0.03/min | First 2 minutes, 3 a day |
| Align a script | align_script | /api/try/align-script | $0.03/min | First 2 minutes, 3 a day |
| Cut | cut_audio | /api/try/cut | $0.01/min | First hour, 10 a day |
| Remove silence | remove_silence | /api/try/remove-silence | $0.01/min | First 3 minutes, 10 a day |
| Set loudness | adjust_loudness | /api/try/loudness | $0.01/min | First 3 minutes, 10 a day |
| Convert | convert_audio | /api/try/convert | $0.01/min | First hour, 10 a day |
| Join files | join_audio | /api/try/join | $0.01/min | First hour, 10 a day |
| Swap a video's audio | replace_audio | /api/try/swap-audio | $0.01/min | First hour, 10 a day |
| Media info | analyze_audio | /api/try/media-info | Free | Whole file, 20 a day |
| Remove filler words | remove_fillers | /api/try/remove-fillers | $0.03/min | First 2 minutes, 3 a day |
| Censor audio | censor_audio | /api/try/censor-audio | $0.03/min | First 2 minutes, 3 a day |
| Translate audio | translate_transcript | /api/try/audio-translator | $0.05/min | First 2 minutes, 3 a day |
| Translate subtitles | translate_subtitles | /api/try/translate-subtitles | $0.05 per 1,000 characters per language | Up to 1,000 chars (3 langs), 3 a day |
| Find highlights | find_highlights | /api/try/find-highlights | $0.04/min | First 10 minutes, 3 a day |
| Shorten transcript | shorten_transcript | /api/try/shorten-transcript | $0.04/min | First 10 minutes, 3 a day |
| Level speakers | level_speakers | /api/try/level-speakers | $0.02/min | First 3 minutes, 3 a day |
| Mix tracks | mix_tracks | /api/try/mix | $0.02/min | First 3 minutes, 3 a day |
| Change speed & pitch | change_speed_pitch | /api/try/speed-pitch | $0.01/min | First 10 minutes, 10 a day |
| Find key & BPM | find_key_bpm | /api/try/key-bpm | Free | Whole file, 20 a day |
| Reverse audio | reverse_audio | /api/try/reverse | $0.01/min | First 10 minutes, 10 a day |
| Mute a video | mute_video | /api/try/mute-video | $0.01/min | First hour, 10 a day |
| Convert video | convert_video | /api/try/mov-to-mp4 | $0.01/min | First 10 minutes, 10 a day |
| Compress video | compress_video | /api/try/video-compressor | $0.01/min | First 10 minutes, 10 a day |
| Crop video | crop_video | /api/try/crop-video | $0.01/min | First 10 minutes, 10 a day |
| Resize video | resize_video | /api/try/resize-video | $0.01/min | First 10 minutes, 10 a day |
| Reverse video | reverse_video | /api/try/reverse-video | $0.01/min | First 10 minutes, 10 a day |
| Loop video | loop_video | /api/try/loop-video | $0.01/min | First 10 minutes, 10 a day |
| Grab a frame | get_frame | /api/try/get-frame | $0.01 per job | 1 job, 10 a day |
| Video to GIF | video_to_gif | /api/try/video-to-gif | $0.01/min | First 5 minutes, 10 a day |
| Add captions | add_captions | /api/try/add-captions | $0.04/min | First 2 minutes, 3 a day |
| Audio to video | audio_to_video | /api/try/audio-to-video | $0.02/min | First 2 minutes, 3 a day |
| Add text and logo | add_overlay | /api/try/add-overlay | $0.01/min | First 10 minutes, 10 a day |
| Plan a reframe | reframe_plan | /api/try/reframe-plan | $0.01/min | First 2 minutes, 3 a day |
| Reframe video | reframe_video | /api/try/reframe-video | $0.03/min | First 2 minutes, 3 a day |
| Text to speech | text_to_speech | /api/try/text-to-speech | $0.05 to $0.20 per 1,000 characters | Up to 300 chars, 3 a day |
| Subtitles to speech | speak_subtitles | /api/try/speak-subtitles | $0.05 to $0.20 per 1,000 characters | Up to 300 chars, 3 a day |
| Voice cloning | clone_voice | /api/try/voice-cloning | $0.12 per 1,000 characters | Up to 300 chars, 3 a day |
| Voice changer | change_voice | /api/try/voice-changer | $0.30/min | First 15 seconds, 2 a day |
| Sound effect generator | generate_sound_effect | /api/try/sound-effect-generator | $0.005 per generated second | Up to 10 s, 3 a day |
| Voice design | design_voice | /api/try/voice-design | $0.02 per job | 1 design (3 previews), 3 a day |
| Generate music | generate_music | /api/try/generate-music | $0.10 to $0.20 per job | 1 track of 30 seconds, 1 a day |
| Separate sound | separate_sound | /api/try/separate-sound | $0.25/min | First 20 seconds, 3 a day |
Every media tool accepts both audio and video (text-input tools such as Text to speech, Voice design, and Translate subtitles take scripts or subtitle files). Tools that only change the sound return the same video with the new sound, with the picture copied. Tools that change timing re-encode the picture.
Files
- Audio in: WAV, MP3, M4A, AAC, FLAC, OGG, Opus, WebM, AIFF. Video in: MP4, MOV, MKV, WebM, AVI.
- Up to 10 GB and 10 hours a file (in parts over 100 MB). Scripts can be up to 2 MB.
- Files are deleted 24 hours after upload, and free results after 1 hour. Download links last 15 minutes.
- Outputs are named after the input, such as interview.wav to interview-clean.wav.
Prices
- Media tools are priced by the minute of input ($0.01 to $0.30/min, above), text-to-speech and voice cloning per 1,000 characters ($0.05 to $0.20), subtitle translation per 1,000 characters per language ($0.05), and frame grabs or voice designs per job ($0.01 to $0.02). Audo counts prices in credits (1 credit is 1¢), so a quote of 175 credits is $1.75 and
max_creditsis in credits too. Minute-billed jobs measure input length to the nearest second, rounded up to a whole credit, and the smallest charge is 1 credit. - A job costs Audo's own measure of the file. The website and the REST API show the price before anything runs (a file's
prices, and the quote), and assistants pay it from your balance. A job is charged only when it succeeds. - Credits don't expire. See pricing.
- Auto-refill keeps apps and agents running: when the balance drops below a threshold the person chose (such as $5), Audo adds a set amount (such as $25) with their saved card at once, up to a monthly limit. When a job is refused for its balance and auto-refill is off, ask the person to turn on auto-refill at https://audo.ai/keys. Only the person can turn it on, change it, or turn it off, on the API page.
GET /api/v1/auto-refill, the account, andget_accountshow it, read-only.
For agents
- llms.txt lists every tool with its curl command.
- The OpenAPI file for the free and REST APIs is at https://audo.ai/api/openapi.json.
- Every page has a Markdown version: add .md to its address, or send
Accept: text/markdown. - Guides for common workflows: Noise Removal & Audio Cleanup API, Free LUFS Loudness & Media Info API, and Audio Cleanup & Transcription in n8n.