ai.wubble/audio

Official28 tools

Wubble

Create, inspect, and manage Wubble music, speech, voice, and sound-effect requests through MCP.

Create and manage music, speech, voice, and sound-effect requests through Wubble.

Captured live from the server via tools/list.

wubble_get_credits

Get Wubble credits. Reads information from the connected Wubble account.

No parameters.

wubble_get_usage

Get Wubble usage. Reads information from the connected Wubble account.

No parameters.

wubble_get_request_status

Get Wubble request status. Reads information from the connected Wubble account.

Parameters (1)

requestIdstringrequired
Wubble request ID to inspect.

wubble_wait_for_request

Wait for Wubble request. Reads information from the connected Wubble account.

Parameters (3)

requestIdstringrequired
Wubble request ID to wait for.
timeout_secondsnumber
Maximum seconds to wait in this tool call. Max 45.
poll_interval_secondsnumber
Seconds between status checks. Max 10.

wubble_list_voices

List Wubble voices. Reads information from the connected Wubble account.

No parameters.

wubble_get_speech_status

Get Wubble speech status. Reads information from the connected Wubble account.

Parameters (1)

requestIdstringrequired
Speech request ID to inspect.

wubble_get_dubbing_transcript

Get Wubble dubbing transcript. Reads information from the connected Wubble account.

Parameters (3)

dubbingIdstringrequired
Dubbing provider/request ID.
language_codestringrequired
Transcript language code.
formatstringrequired
Transcript format.

wubble_upload_audio

Upload Wubble audio. Consumes Wubble requests or credits.

Parameters (4)

source_urlstringrequired
HTTPS URL for MCP to fetch and upload to Wubble.
filenamestring
Optional filename for the uploaded audio.
content_typestring
Optional media content type.
purposestring
Optional upload purpose.

wubble_upload_vocal

Upload Wubble vocal. Consumes Wubble requests or credits.

Parameters (3)

source_urlstringrequired
HTTPS URL for MCP to fetch and upload as a vocal reference.
filenamestring
Optional filename for the uploaded vocal.
content_typestring
Optional media content type.

wubble_generate_song

Generate Wubble song. Consumes Wubble requests or credits.

Parameters (2)

promptstringrequired
Description of the song to generate.
lyricsstring
Optional lyrics to use for the song.

wubble_generate_instrumental

Generate Wubble instrumental. Consumes Wubble requests or credits.

Parameters (1)

promptstringrequired
Description of the instrumental track to generate.

wubble_generate_lyrics

Generate Wubble lyrics. Consumes Wubble requests or credits.

Parameters (2)

promptstringrequired
Description of the lyrics to generate.
stylestring
Optional lyric style.

wubble_extend_lyrics

Extend Wubble lyrics. Consumes Wubble requests or credits.

Parameters (2)

lyricsstringrequired
Existing lyrics to extend.
promptstring
Optional direction for the extension.

wubble_extend_song

Extend Wubble song. Consumes Wubble requests or credits.

Parameters (6)

song_idstringrequired
Caller-owned completed song request ID.
lyricsstringrequired
Lyrics for the extension.
extend_atnumberrequired
Extension position in milliseconds.
extend_typestring
Where to extend the song.
modelstring
Optional model.
promptstring
Optional extension prompt.

wubble_analyze_lyrics

Analyze Wubble lyrics. Consumes Wubble requests or credits.

Parameters (1)

upload_audio_idstringrequired
Uploaded Wubble audio ID to analyze.

wubble_describe_audio

Describe Wubble audio. Consumes Wubble requests or credits.

Parameters (2)

urlstringrequired
Wubble-owned or user-provided audio URL to describe.
modelstring
Optional model.

wubble_separate_stems

Separate Wubble stems. Consumes Wubble requests or credits.

Parameters (2)

urlstringrequired
Wubble-owned or user-provided audio URL for stem separation.
modelstring
Optional model.

wubble_remix_song

Remix Wubble song. Consumes Wubble requests or credits.

Parameters (5)

song_idstring
Caller-owned completed song request ID.
upload_audio_idstring
Uploaded Wubble audio ID.
lyricsstringrequired
Lyrics for the remix.
promptstring
Optional remix prompt.
nnumber
Optional number of variations.

wubble_generate_track

Generate Wubble track. Consumes Wubble requests or credits.

Parameters (8)

generate_typestringrequired
Track type to generate.
song_idstring
Caller-owned completed song request ID.
upload_audio_idstring
Uploaded Wubble audio ID.
generate_startnumber
Start time in milliseconds.
generate_endnumber
End time in milliseconds.
lyricsstring
Optional lyrics.
promptstring
Optional generation prompt.
vocal_genderstring
Optional vocal gender.

wubble_edit_track

Edit Wubble track. Consumes Wubble requests or credits.

Parameters (6)

track_idstring
Caller-owned track/song request ID.
upload_audio_idstring
Uploaded Wubble audio ID.
edit_startnumberrequired
Edit region start in milliseconds.
edit_endnumberrequired
Edit region end in milliseconds.
lyricsstring
Optional replacement lyrics.
source_duration_msnumber
Optional source duration in milliseconds.

wubble_create_podcast

Create Wubble podcast. Consumes Wubble requests or credits.

Parameters (4)

promptstringrequired
Podcast topic or direction.
voicesarray
background_musicboolean
Whether to include background music.
conversationsarray

wubble_text_to_speech

Generate Wubble speech. Consumes Wubble requests or credits.

Parameters (6)

textstringrequired
Text to synthesize.
voice_idstring
Optional Wubble voice ID.
model_idstring
Optional model ID.
voice_settingsobject
Optional voice settings.
language_codestring
Optional language code.
output_formatstring
Optional output format. Use mp3_44100_128 for MP3 audio; shorthand mp3 is accepted and normalized.

wubble_speech_to_text

Transcribe Wubble speech. Consumes Wubble requests or credits.

Parameters (7)

source_urlstringrequired
HTTPS URL for MCP to fetch and transcribe.
model_idstring
Optional model ID.
timestamps_granularitystring
Timestamp granularity.
diarizeboolean
Whether to diarize speakers.
detect_speaker_rolesboolean
Whether to detect speaker roles.
keytermsarray
language_codestring
Optional language code.

wubble_isolate_voice

Isolate Wubble voice. Consumes Wubble requests or credits.

Parameters (2)

source_urlstringrequired
HTTPS URL for MCP to fetch and isolate vocals from.
file_formatstring
Optional file format.

wubble_text_to_dialog

Generate Wubble dialog. Consumes Wubble requests or credits.

Parameters (8)

inputsarrayrequired
model_idstring
Optional model ID.
language_codestring
Optional language code.
settingsobject
Optional dialog settings.
pronunciation_dictionary_locatorsarray
seednumber
Optional deterministic seed.
apply_text_normalizationstring
Text normalization mode.
output_formatstring
Optional output format.

wubble_change_voice

Change Wubble voice. Consumes Wubble requests or credits.

Parameters (5)

source_urlstringrequired
HTTPS URL for MCP to fetch and convert.
target_voice_idstringrequired
Target Wubble voice ID.
model_idstring
Optional model ID.
file_formatstring
Optional file format.
output_formatstring
Optional output format.

wubble_dub_audio

Dub Wubble audio. Consumes Wubble requests or credits.

Parameters (13)

source_urlstringrequired
HTTPS URL for MCP to fetch and dub.
target_langstringrequired
Target language code.
source_langstring
Optional source language code.
namestring
Optional dubbing job name.
num_speakersnumber
Optional number of speakers.
watermarkboolean
Whether to watermark output.
start_timenumber
Optional start time.
end_timenumber
Optional end time.
highest_resolutionboolean
Whether to request highest resolution.
drop_background_audioboolean
Whether to drop background audio.
use_profanity_filterboolean
Whether to use profanity filter.
dubbing_studioboolean
Whether to enable dubbing studio.
disable_voice_cloningboolean
Whether to disable voice cloning.

wubble_generate_sound_effect

Generate Wubble sound effect. Consumes Wubble requests or credits.

Parameters (5)

textstringrequired
Sound effect description.
duration_secondsnumber
Optional duration from 0.5 to 30 seconds.
prompt_influencenumber
Optional prompt influence from 0 to 1.
loopboolean
Whether the sound effect should loop.
output_formatstring
Optional output format.

Install

claude_desktop_config.json

{
  "mcpServers": {
    "audio": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.wubble.ai/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.