Audio tools
Convert, trim, join and level audio, draw waveforms, and prepare recordings for speech-to-text. Every tool here is free, needs no account, and works three ways: in this page, over plain HTTP, and from an AI agent over MCP.
- Tools
- 16
- Instant
- 0
- File upload
- 16
- Interfaces
- UI · HTTP · MCP
Audio
-
Audio file info fileShow the format, length, bitrate, codec, sample rate, channels and tags of an audio file, plus its peak and average volume.
audio-info -
Audio spectrogram image fileDraw a spectrogram of an audio file as a PNG: time across, pitch upwards, brightness for loudness.
audio-spectrogram -
Audio waveform image fileDraw the waveform of an audio file as a PNG picture, in the size and colours you choose.
audio-waveform -
Change audio speed fileSpeed audio up or slow it down from 0.5x to 4x, keeping the pitch natural or letting it rise and fall.
audio-speed -
Convert audio fileConvert audio between MP3, WAV, OGG, Opus, FLAC and M4A, or pull the sound out of a video as an audio file.
audio-convert -
Fade audio in and out fileAdd a fade in at the start and a fade out at the end of an audio file, with a choice of fade shape.
audio-fade -
Find silence in audio fileList every silent stretch in a recording with its start, end and length, and total up silence and sound.
audio-silence-detect -
Join audio files fileJoin 2 to 20 audio files end to end into one, in the order given, with an optional gap or crossfade between them.
audio-concat -
Mix audio files together fileLayer 2 to 8 audio files on top of each other, such as a voice over music, with a volume for each file.
audio-mix -
Normalise audio loudness fileMake audio louder or quieter to hit a standard loudness in LUFS, without clipping. Measures first, then adjusts.
audio-normalize -
Prepare audio for speech-to-text fileTurn any recording or video into the 16 kHz mono 16-bit WAV that Whisper and other speech-to-text models expect.
audio-to-stt-wav -
Resample audio fileChange the sample rate, mono or stereo, and bit depth of an audio file, for devices and software that need a set format.
audio-resample -
Split audio on silence fileCut a recording into separate files at its pauses, for example one file per track, sentence or speaker turn.
audio-split-on-silence -
Test tone generator fileGenerate a test tone as an audio file: sine, square or sawtooth wave at the frequency, length and volume you choose.
audio-tone -
Trim audio fileCut a section out of an audio file by start and end time, with optional fade in and fade out.
audio-trim -
Trim silence from audio fileRemove the silence at the start and end of a recording, leaving the pauses in the middle untouched.
audio-silence-trim
No tool matches that filter. Try clearing the search or switching execution mode.
Explore other categories
// universal contract
One call shape for every tool
curl -s https://setget.net/v1/tools/json-format \
-H 'Content-Type: application/json' \
-d '{"input": {"text": "{\"b\":1,\"a\":2}", "sort_keys": true}}'
claude mcp add --transport http setget https://setget.net/mcp
# then ask: "use setget to find a tool that converts CSV to JSON and run it on this file"
The agent calls find_tools, then run_tool. Setup for other clients.
curl -s 'https://setget.net/v1/tools/search?q=csv+to+json'
Limits: 1 MiB per request, 5 seconds of run time, 10 requests a second and 5,000 calls a day per network address. When something goes wrong the response says what happened and how to fix it; every code is explained under error codes.