AI song generator: sings your lyrics with real vocals in 50 languages, returns a song link
Scored across 3 tools
The three tools have clearly distinct purposes: creating a song, checking its status, and submitting server feedback. There is essentially no risk of confusing song generation with status polling or meta-feedback.
All names use snake_case, but the word-order pattern is mixed: create_song is verb_noun, feedback_add is noun_verb, and song_status is noun_noun. The names are still readable, but they do not follow a predictable convention.
Three tools is a lean but reasonable surface for a focused song-generation service: create, poll, and feedback. It is slightly under-scoped because there is no cancel, list, or retrieval operation, but the count itself is not excessive.
The core create-and-poll workflow is covered, and failed songs report reasons. However, there is no way to list existing songs, cancel a queued song, retry a failed generation, or fetch a song by identifier beyond the immediate status flow, leaving notable lifecycle gaps.
Queues a song with real vocals to YOUR finished lyrics and immediately returns a link to its page with two versions to choose from. The song itself is usually ready in 15–60 seconds.
LANGUAGE: write the lyrics in the language the person speaks to you (or asks for) and pass its ISO code in language. Russian songs live on opensoundbox.ru, all other languages on opensoundbox.com — the server picks the site itself; just give the person the link it returns. 50 languages are supported; checked and sounding good: English, Russian, Spanish, German, French, Italian, Portuguese, Polish, Ukrainian, Chinese, Japanese, Korean, Turkish, Hindi (others may sound less clear).
HOW TO WRITE THE LYRICS (the server sings them as is, without edits):
tag sections in square brackets on their own line: [Verse], [Chorus], optionally [Bridge], [Outro];
clear rhythm and rhyme, 6–10 syllables per line, natural conversational language;
put the person's name, the occasion and details in the lyrics; keep the chorus short, catchy and repeated;
length to match the song: up to 45 s — one 4-line verse, a 4-line chorus, then the chorus again; up to 60 s — one 4-line verse, a 4-line chorus, then the chorus again; up to 120 s — two 4-line verses, a 4-line chorus after each verse, an optional short bridge; up to 240 s — three 4-line verses, a 4-line chorus after each verse, a 2–4 line bridge; up to 300 s — four 4-line verses, a 4-line chorus after each verse (write every chorus repeat in full), a 4-line bridge — about 40 lines in total;
one language and one alphabet per song; don't mix alphabets in one line;
ORIGINAL lines only: lyrics quoting well-known songs or poems are rejected, and so are lyrics with profanity. The sound is set by style, voice and an optional description (instruments, tempo, mood).
Inputs: lyrics (required), language (required), style, title, +3 more.
FEEDBACK ABOUT THIS SERVER ITSELF, not about a song. Call it when a tool behaved differently from its description, when a parameter or response field was missing, or when a refusal came without a clear reason. Be specific: the tool, what you called, what you expected, what you got — a human reads it.
Inputs: title (required), body, kind, tool.
Song status by song_id from create_song: queued — waiting in line, singing — being sung, ready — the versions are done (audio links included), failed — it didn't work (reason in message; failed songs aren't counted). Call at most once every 10 seconds. The page link works before the song is ready too.
Inputs: song_id (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
AI music studio: song generation with vocals, covers, stems, voice conversion, mastering, editing.
Make a finished AI song with real vocals from a brief, or search and stream StarSinger's AI catalog
Make songs, change one part's lyrics in the same voice, and reimagine songs in new styles.
Generate full songs with vocals, instrumentals and sound effects from text. One server for Suno, Google Lyria, Mureka, MiniMax, ACE-Step, YuE and ElevenLabs. Your agent can quote the credit cost before generating, start a song, wait for it to finish and return download links. Sign in with OAuth; optional daily credit caps; retries never charge twice.
Add one secure layer between your agents and this server.
