Skip to main content
Glama

Server Details

AI audio tools for music producers — stem splitting, vocal removal, BPM & key detection, audio-to-MIDI, format conversion, trimming, video-to-audio extraction and AI song generation.

Status
Healthy
Last Tested
Transport
Streamable HTTP
URL

Glama MCP Gateway

Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.

MCP client
Glama
MCP server

Full call logging

Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.

Tool access control

Enable or disable individual tools per connector, so you decide what your agents can and cannot do.

Managed credentials

Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.

Usage analytics

See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.

100% free. Your data is private.
Tool DescriptionsA

Average 4.1/5 across 8 of 8 tools scored.

Server CoherenceA
Disambiguation5/5

Each tool targets a unique audio processing task (e.g., BPM/key detection, format conversion, stem splitting) with no functional overlap, ensuring agents can easily distinguish between them.

Naming Consistency5/5

All tool names follow a strict `boost_audio_verb_noun` pattern in snake_case, providing a predictable and clean naming convention across the entire set.

Tool Count5/5

With exactly 8 tools, the server is well-scoped for an audio processing domain—comprehensive enough to cover key tasks without being overwhelming or sparse.

Completeness4/5

The tools cover essential audio operations (conversion, extraction, generation, splitting, trimming, etc.), but a merging or concatenation tool is missing, leaving a minor gap.

Available Tools

10 tools
boost_audio_ai_readerBoost Audio - AI Reader (TTS)Inspect

Generate natural speech from text using Boost Audio AI. Supports 23 languages. Adjust voice expression from calm to very expressive. Use this when the user wants to convert text to audio, create a voiceover, narrate content, or listen to text read aloud. Returns a downloadable WAV audio file.

ParametersJSON Schema
NameRequiredDescriptionDefault
textNoText to synthesize into speech. Maximum ~200 words for FREE tier, ~500 for Producer, unlimited for Ultimate. Leave empty to open the widget for interactive input.
_actionNoInternal action selector. 'generate' synthesizes speech (default), 'languages' returns the supported language list.
_inlineNoInternal flag set by the widget to drive the generation pipeline.
languageNoLanguage code for synthesis (e.g. 'pl', 'en', 'de'). Defaults to 'pl'. The voice model is optimized for the selected language.
exaggerationNoVoice expressiveness level from 0.0 (calm, neutral) to 1.0 (very expressive, dramatic). Default 0.5. Use lower values for narration, higher for dramatic reading.
reference_audio_urlNoURL of a reference audio file to clone the voice from. Available on Ultimate (PRO) tier only. Must be a boost.audio-hosted voice URL.
boost_audio_bpm_key_finderBoost Audio - BPM and Key FinderInspect

Detect the BPM (tempo) and musical key of an audio file. Use this when the user asks for the tempo, key, scale or harmonic information of a song.

ParametersJSON Schema
NameRequiredDescriptionDefault
audio_urlNoOptional public URL to an audio/video file. If omitted, the user uploads the file in the rendered widget.
file_nameNoOriginal file name. Required when audio_base64 is provided.
file_typeNoOriginal mime type. Required when audio_base64 is provided.
file_tokenNoToken for a pre-uploaded large file (>22 MB). Obtained from POST /widget-api/upload-raw. Used instead of audio_base64 for large files.
audio_base64NoOptional base64-encoded audio file payload. Used by the widget when the host iframe blocks CORS fetches.
boost_audio_converterBoost Audio - Audio ConverterInspect

Convert audio files between MP3, WAV, FLAC, OGG and M4A. Use this when the user wants to change the format of an audio file (e.g. WAV to MP3, MP3 to FLAC).

ParametersJSON Schema
NameRequiredDescriptionDefault
audio_urlNoOptional public URL to an audio/video file. If omitted, the user uploads the file in the rendered widget.
file_nameNoOriginal file name. Required when audio_base64 is provided.
file_typeNoOriginal mime type. Required when audio_base64 is provided.
file_tokenNoToken for a pre-uploaded large file (>22 MB). Obtained from POST /widget-api/upload-raw. Used instead of audio_base64 for large files.
audio_base64NoOptional base64-encoded audio file payload. Used by the widget when the host iframe blocks CORS fetches.
target_formatNoOutput format. Defaults to mp3.mp3
boost_audio_extract_audio_from_videoBoost Audio - Extract Audio from VideoInspect

Extract the audio track from MP4, MOV, WebM or M4V video and download as MP3 or WAV. Use this when the user wants to get audio out of a video file.

ParametersJSON Schema
NameRequiredDescriptionDefault
audio_urlNoOptional public URL to an audio/video file. If omitted, the user uploads the file in the rendered widget.
file_nameNoOriginal file name. Required when audio_base64 is provided.
file_typeNoOriginal mime type. Required when audio_base64 is provided.
file_tokenNoToken for a pre-uploaded large file (>22 MB). Obtained from POST /widget-api/upload-raw. Used instead of audio_base64 for large files.
audio_base64NoOptional base64-encoded audio file payload. Used by the widget when the host iframe blocks CORS fetches.
target_formatNoOutput audio format. Defaults to mp3.mp3
boost_audio_song_generatorBoost Audio - AI Song GeneratorInspect

Generate a full audio track from a text prompt using Boost Audio AI. Returns a mix and optionally separated stems openable in the Boost Audio DAW. Use this when the user wants AI-generated music, an instrumental, a song with lyrics or a quick demo from an idea.

ParametersJSON Schema
NameRequiredDescriptionDefault
bpmNoOptional tempo in beats per minute (60-180).
styleNoLegacy alias — folded into `inspiration` if provided (e.g. 'lofi hiphop'). Prefer `inspiration` and `styles` instead.
_jobIdNoInternal: job id returned by 'start'. Required when `_action='poll'`.
promptNoIdea for the song. When `lyrics_mode='auto'` the AI uses this as the subject; when `lyrics_mode='write'` the contents become the actual lyrics. Equivalent to the 'Pomysł lub tekst / Idea or lyrics' field on boost.audio.
stylesNoUp to 6 style preset ids from `/tools/song-styles` (e.g. ['lofi-hip-hop','synthpop','ambient']). Use `_action='styles'` to fetch the catalogue.
_actionNoInternal action selector used by the widget. 'start' kicks off generation, 'poll' returns the current status, 'lyrics' asks Boost Audio AI to draft lyrics, 'styles' returns the style preset catalogue.
_inlineNoInternal flag set by the widget when it wants the MCP server to drive the generation pipeline.
durationNoTrack length in seconds (30-180). Defaults to 120.
key_scaleNoOptional musical key, e.g. 'A minor' or 'C major'.
_pollSecretNoInternal: poll secret returned by 'start'. Required when `_action='poll'`.
inspirationNoStyle, inspiration and arrangement notes (e.g. 'modern pop with synths, intimate vocal, wide chorus'). Maps to the 'Styl, inspiracje i instrukcje / Style, inspiration and instructions' field on boost.audio.
lyrics_modeNo'auto' = AI writes lyrics from your idea (default). 'write' = treat `prompt` as ready-to-sing lyrics.
instrumentalNoIf true, no vocals are generated. Defaults to false.
boost_audio_stem_splitterBoost Audio - Stem SplitterInspect

Split a song into separate stems with Boost Audio AI: vocals, drums, bass and other (4-stem mode). Ultimate plan unlocks a 6-stem mode with separate guitar and piano. Use this when the user wants individual instrument stems.

ParametersJSON Schema
NameRequiredDescriptionDefault
modeNoStem separation mode. 6-stem requires Ultimate plan.4-stem
audio_urlNoOptional public URL to an audio/video file. If omitted, the user uploads the file in the rendered widget.
file_nameNoOriginal file name. Required when audio_base64 is provided.
file_typeNoOriginal mime type. Required when audio_base64 is provided.
file_tokenNoToken for a pre-uploaded large file (>22 MB). Obtained from POST /widget-api/upload-raw. Used instead of audio_base64 for large files.
audio_base64NoOptional base64-encoded audio file payload. Used by the widget when the host iframe blocks CORS fetches.
boost_audio_studio_builderBoost Audio - Studio BuilderInspect

Open Soundra-style studio wizard inside this conversation. Asks the user 4 short questions (purpose, genre, budget, room size) and builds 3 studio proposals (budget / optimal / premium) with hardware per slot (microphone, audio interface, monitors, headphones, MIDI controller, DAW) and direct purchase links to supersound.pl with UTM tracking. Use when the user asks to recommend studio gear, plan a home studio for X PLN/EUR, swap a device, or compare price tiers. IMPORTANT: ALWAYS pass locale (pl/en/de) inferred from the user's chat language so prices are localized (PL=PLN, EN/DE=EUR) and product names + supersound.pl URLs are returned in the right language.

ParametersJSON Schema
NameRequiredDescriptionDefault
nameNoSetup name for `_action='save'`. Defaults to 'Setup z MCP — {timestamp}'.
slotNoOptional slot id for `_action='search'` (e.g. 'microphone', 'interface'). Goes into `utm_content` for finer attribution.
itemsNoSetup payload for `_action='save'`. Free-form object — typically `{ slots: {...}, accessories: [...], total_price: number }`.
limitNoOptional result limit for `_action='search'` (1-20, default 6).
budgetNoTotal budget in PLN (or EUR for en/de locale). Required for `_action='build'`. Distributed across slots according to `purpose`. Range: 500-50000.
localeNoLocalizes prices (PL=PLN, EN/DE=EUR) and supersound.pl shop URL prefix (/eu/ for EN, /de/ for DE).
searchNoFree-text search for `_action='search'`, e.g. 'Shure SM7B' or 'Focusrite Scarlett'.
_actionNoAction selector. 'build' (default): generate 3 proposals from budget+purpose. 'search': find specific products by category. 'get_mine': list saved setups (OAuth). 'save': persist current setup to user's account (OAuth).
purposeNoPrimary use case. Drives slot allocation: 'vocal'=mic/interface heavy, 'podcast'=mic 35%/interface 20%, 'beat-making'=MIDI 20%/monitors 25%, 'production'=balanced studio, 'general'=balanced.
categoryNoProduct category for `_action='search'`. Aliases internally to WooCommerce category slugs.
max_priceNoOptional max price filter for `_action='search'`.
min_priceNoOptional min price filter for `_action='search'`.
room_sizeNoRoom size hint (informational, used by widget for monitor pair size suggestions).
total_priceNoOptional total price hint for `_action='save'`.
conversation_idNoOptional conversation/session id from the LLM client. Goes into `utm_term` for sales attribution per chat session.
boost_audio_to_midiBoost Audio - Audio to MIDIInspect

Convert a melody or drum track from audio to a downloadable MIDI file. Use midi_mode='melody' (default) for pitched instruments/vocals, 'drums' for drum transcription.

ParametersJSON Schema
NameRequiredDescriptionDefault
audio_urlNoOptional public URL to an audio/video file. If omitted, the user uploads the file in the rendered widget.
file_nameNoOriginal file name. Required when audio_base64 is provided.
file_typeNoOriginal mime type. Required when audio_base64 is provided.
midi_modeNo'melody' for pitched instruments/vocals (default), 'drums' for drum transcription.melody
stem_hintNoInstrument type hint for melody mode — helps the transcription engine. Ignored when midi_mode is 'drums'.other
file_tokenNoToken for a pre-uploaded large file (>22 MB). Obtained from POST /widget-api/upload-raw. Used instead of audio_base64 for large files.
audio_base64NoOptional base64-encoded audio file payload. Used by the widget when the host iframe blocks CORS fetches.
boost_audio_trimmerBoost Audio - Audio TrimmerInspect

Trim a section of an MP3 or WAV file with optional fade in/out. Use this when the user wants to cut a fragment from a longer recording.

ParametersJSON Schema
NameRequiredDescriptionDefault
end_secNoEnd of the kept range, in seconds.
fade_inNoFade-in length in seconds (default 0).
fade_outNoFade-out length in seconds (default 0).
audio_urlNoOptional public URL to an audio/video file. If omitted, the user uploads the file in the rendered widget.
file_nameNoOriginal file name. Required when audio_base64 is provided.
file_typeNoOriginal mime type. Required when audio_base64 is provided.
start_secNoStart of the kept range, in seconds.
file_tokenNoToken for a pre-uploaded large file (>22 MB). Obtained from POST /widget-api/upload-raw. Used instead of audio_base64 for large files.
audio_base64NoOptional base64-encoded audio file payload. Used by the widget when the host iframe blocks CORS fetches.
boost_audio_vocal_removerBoost Audio - Vocal RemoverInspect

Separate vocals from instrumental in MP3/WAV using Boost Audio AI. Use this when the user wants to isolate vocals (acapella) or get an instrumental version of a song.

ParametersJSON Schema
NameRequiredDescriptionDefault
audio_urlNoOptional public URL to an audio/video file. If omitted, the user uploads the file in the rendered widget.
file_nameNoOriginal file name. Required when audio_base64 is provided.
file_typeNoOriginal mime type. Required when audio_base64 is provided.
file_tokenNoToken for a pre-uploaded large file (>22 MB). Obtained from POST /widget-api/upload-raw. Used instead of audio_base64 for large files.
audio_base64NoOptional base64-encoded audio file payload. Used by the widget when the host iframe blocks CORS fetches.

Discussions

No comments yet. Be the first to start the discussion!

Try in Browser

Your Connectors

Sign in to create a connector for this server.

Resources