Skip to content
audo

Audio and Video Tools for AI Agents: Claude Code, Codex, Cursor, OpenCode, and More

How terminal agents, IDE agents, chat assistants, and custom Python or TypeScript agents clean up, edit, split, and transcribe audio and video files.

Updated November 5, 2026Michael NguyenTested October 2026

Try Remove noise from Audo

Most

From keep some background to remove most.

More options
Free for the first minute, 3 times a day. No sign-up.

Quick answer

Local command-line libraries like MoviePy, SoX, and pydub let a coding agent trim a clip or change its container, but they can't remove room echo, separate speakers in a transcript, cut filler words, bleep swear words while keeping background music, generate or clone voices, split vocals and instruments, or compose royalty-free music and sound effects without GPU and cloud models. Audo AI gives any AI agent 44 studio audio, video, voice, music, and sound-effect tools plus multi-step workflows in three ways: a remote HTTP MCP server (https://audo.ai/mcp, with find_tools discovery) for Claude Code, Codex, Cursor, OpenCode, Gemini CLI, VS Code, Copilot CLI, Zed, Antigravity, ChatGPT, Claude, Cowork, and Raycast; a one-call Free API (POST https://audo.ai/api/try/<tool>) that works with curl and no API key; and a keyed REST API (/api/v1/jobs, /api/v1/voices, /api/v1/tools/find) with an OpenAPI spec for custom agent frameworks and n8n.

How different AI agents and frameworks connect to Audo AI (checked November 2026)
Agent or frameworkHow it connectsHow local files moveFree tier & whole-file pricing
Claude Code, Codex, Gemini CLI, Copilot CLI, OpenCodeRemote HTTP MCP (https://audo.ai/mcp) or one-call curl to /api/try/<tool>Agent uploads local files with curl and saves the finished file next to the originalFree allowance on every tool (no key for /api/try); $0.01–$0.30/min or $0.05–$0.20/1k chars paid
Cursor, VS Code, Zed, AntigravityOne-click MCP install or JSON config (https://audo.ai/mcp) with browser OAuthIDE agent uploads project files with curl and writes outputs into the workspaceSame free tier as the website; pay-as-you-go credits from $5, no subscription
ChatGPT, Claude, Cowork, RaycastCustom connector / app pointing to https://audo.ai/mcp with OAuth sign-inChat upload widget, public URL, or a one-time 10 GB browser upload link from add_fileSame free tier; returns a one-click finish link when a file exceeds the free preview
OpenAI Agents SDK, Claude Agent SDK, Vercel AI SDK, LangGraph, CrewAI, PydanticAI, n8nRemote MCP server, OpenAPI spec (https://audo.ai/api/openapi.json), or REST API (/api/v1/jobs)Direct HTTPS URLs, multipart uploads up to 10 GB, and signed download linksFree API without a key; Bearer $AUDO_API_KEY + optional auto-refill for unattended runs

Hear the difference

Play Original, then Cleaned.

Cleaned removes the chatter and dishes.

Made with Remove noise

What local libraries (MoviePy, SoX, pydub) do vs. what Audo AI adds

When you ask a coding agent to edit an audio or video file, it usually reaches for whatever command-line tool or Python package is installed on the machine. That works for simple mechanical edits, and hits a wall as soon as the task needs speech or music models.

Combining local scripts with Audo AI's MCP server or API lets the agent handle both:

  • Neural voice clean-up and echo removal (remove_noise, enhance_voice)

    Standard command-line spectral gates (like afftdn or arnndn) muffle speech when background noise changes. Audo AI's remove_noise strips wind, traffic, café chatter, and music while keeping the speaker's real voice, and enhance_voice removes hollow room echo and restores muffled laptop or phone mics ($0.05 a minute, first minute free).

  • Stereo stem splitting for songs and videos (split_audio)

    Separates a song into vocals and instrumental (or 4 stems: vocals, drums, bass, and other), or splits a video's soundtrack into dialogue, background music, and sound effects while copying the original video picture untouched ($0.08 a minute, first 45 seconds free).

  • Speaker-labeled transcription and script alignment (transcribe_audio, align_script)

    Transcribes recordings up to 10 hours in 60 languages with labels for up to 8 speakers and exact start and end times for every word, returning TXT, SRT, VTT, and JSON in one run ($0.03 a minute, first 2 minutes free).

  • Filler words, profanity bleeping, pauses, speaker leveling, and LUFS (remove_fillers, censor_audio, remove_silence, level_speakers, analyze_audio)

    Cuts ums, uhs, and repeated phrases in the quiet between words ($0.03 a minute), bleeps or mutes swear words and custom phrases in place with optional vocal separation so music keeps playing ($0.03 a minute, +$0.05 a minute to keep the background), shortens dead air ($0.01 a minute), balances loud hosts and quiet guests ($0.02 a minute), and measures integrated LUFS, true peak, noise floor, and clipping for free ($0.00, 20 files a day).

  • Royalty-free AI music, sound effects, AI voices, subtitle dubbing, voice cloning, voice design, and speech-to-speech (generate_music, generate_sound_effect, text_to_speech, speak_subtitles, clone_voice, design_voice, change_voice)

    Composes 44.1 kHz stereo MP3 podcast intros, background beds, jingles, or songs with custom lyrics using Google's Lyria 3.5 and Lyria 3 Clip ($0.10–$0.20 a track, a 30-second track/day free), generates 0.5–30 s MP3 or 48 kHz WAV sound effects and seamless loops with ElevenLabs SFX v3 ($0.005/s, up to 10 s free 3x/day), reads scripts or timed SRT/VTT subtitles (with optional video dubbing and auto-ducking) on Text to speech and SRT to speech ($0.05–$0.20 per 1,000 characters), designs new voices on Voice design ($0.02 per set of 3 previews) and reads scripts in a cloned or saved voice on Voice cloning ($0.12 per 1,000 characters), with voices kept via save_voice and list_voices, and swaps speakers on Voice changer ($0.30 a minute).

Three ways an AI agent can call Audo AI

Every Audo AI surface runs the same 44 tools, plain-language tool discovery (`find_tools` / `POST /api/v1/tools/find`), and multi-step workflows (`podcast_ready`, `fix_video_sound`, `clips`, `meeting_shortener`), with the same free tier and pay-as-you-go prices:

  • 1. Remote HTTP MCP server (https://audo.ai/mcp)

    In Claude Code, run `claude mcp add --transport http --scope user audo https://audo.ai/mcp`. In Codex, run `codex mcp add audo --url https://audo.ai/mcp`. In Gemini CLI, run `gemini mcp add --transport http --scope user audo https://audo.ai/mcp`. Cursor, VS Code, OpenCode, Zed, Antigravity, ChatGPT, Claude, Cowork, and Raycast connect to the same URL on /setup.

  • 2. One-call Free API with curl (no API key or sign-up)

    Any agent with bash or HTTP access can send `curl -F file=@interview.wav https://audo.ai/api/try/remove-noise -D response.headers -o response.body` (or `/api/try/enhance-voice`, `/api/try/transcribe`, `/api/try/media-info`) right away with no account or key for the free part of each file.

  • 3. Keyed REST API (/api/v1/jobs) and OpenAPI spec

    For custom agents built with the OpenAI Agents SDK, Claude Agent SDK, Vercel AI SDK, LangGraph, CrewAI, PydanticAI, or n8n, pass `Authorization: Bearer $AUDO_API_KEY` to process full files up to 10 hours and 10 GB, with optional auto-refill on /keys.

How a coding agent chains a full podcast or video edit

When you tell Claude Code, Codex, Cursor, or OpenCode to clean up and publish a raw episode or interview in your project folder, the agent can chain Audo's tools in order:

  • Step 1: Inspect the recording for free (analyze_audio)

    The agent calls `analyze_audio` (or `POST /api/try/media-info`) at $0.00 to read integrated LUFS, true peak dBTP, RMS noise floor, clipped samples, and silent timestamp ranges before deciding which clean-up steps the file needs.

  • Step 2: Clean the voice and balance the speakers (remove_noise, enhance_voice, level_speakers)

    The agent runs `remove_noise` if the background is noisy, `enhance_voice` if the room echoes, and `level_speakers` if one person is quieter than the other. On a video file, the picture stays untouched.

  • Step 3: Tighten fillers and pauses, then transcribe (remove_fillers, remove_silence, transcribe_audio)

    The agent removes ums and uhs, shortens long silences, normalizes loudness to -16 LUFS for podcasts (or -14 LUFS for YouTube), and generates speaker-labeled TXT show notes plus SRT and VTT captions next to the original file.

When a local command-line tool or the browser editor is the better choice

Use each tool for the part of the job it does best:

  • Local command-line tools (SoX, MoviePy, pydub)

    If your agent is already running on a machine with local media binaries and only needs to slice a known timestamp range, concatenate two identical WAV files, or read a file header offline with zero network traffic.

  • Audo AI's browser tools and waveform editor

    If you want to audition Original and Cleaned audio side by side at the same playhead, drag a strength slider by ear, or visually uncheck individual filler-word cuts on a waveform before exporting.

  • Audo AI via MCP or API

    Whenever an agent needs speech-aware noise removal, room echo removal, 4-stem song or 3-stem video separation, multi-speaker transcription in 60 languages, speaker leveling, or cloud media processing without installing local weights or GPUs.

Add Audo AI to your agent in one minute

Connect ChatGPT, Claude, Claude Code, Codex, Cursor, OpenCode, Gemini CLI, or VS Code to https://audo.ai/mcp, or call the free API with curl. Free to try. No sign-up.

Questions

How can I let Claude Code, Codex, or Cursor clean up and edit my podcast audio?

Add Audo AI's MCP server (`https://audo.ai/mcp`): for example `claude mcp add --transport http --scope user audo https://audo.ai/mcp` in Claude Code, `codex mcp add audo --url https://audo.ai/mcp` in Codex, or one click in Cursor and VS Code. Then ask the agent in plain words to remove background noise, fix echo, cut filler words, shorten silences, level speakers, and transcribe the recording in your folder.

Can an AI agent call Audo AI without an API key or MCP setup?

Yes. Any agent that can run `curl` or make an HTTP POST request can call Audo AI's keyless endpoint at `POST https://audo.ai/api/try/<tool>` (such as `/api/try/remove-noise`, `/api/try/enhance-voice`, `/api/try/transcribe`, or `/api/try/media-info`) with no API key and no sign-up for the free part of each file.

Which AI agents and IDEs work with Audo AI's MCP server?

Audo AI's MCP server works with any client that supports remote HTTP MCP servers: Claude Code, OpenAI Codex, Cursor, OpenCode, Gemini CLI, VS Code, GitHub Copilot CLI, Zed, Antigravity, ChatGPT (Developer mode), Claude, Cowork, and Raycast, plus custom agents built with the OpenAI Agents SDK, Claude Agent SDK, Vercel AI SDK, LangGraph, CrewAI, or PydanticAI.

How does an AI agent handle large video files up to 10 GB?

Terminal and IDE agents upload local files straight to Audo's signed upload URLs with `curl` (including multipart uploads over 100 MB up to 10 GB). Chat assistants like ChatGPT and Claude call `add_file` and give you a private browser link where you can drop files up to 10 GB.

How do I prevent an unattended agent from spending too many credits?

Over Audo AI's MCP server, an agent spends from your prepaid balance, so the balance is the limit, and auto-refill is off unless you turn it on, with a monthly cap you set. Through the REST API, a call can also pass `free: true` (only the free tier, never spending credits) or `max_credits` (a cap in credits, where 1 credit is 1 US cent; a job over it doesn't start). You are only charged when a job succeeds.