AI song generator: sings your lyrics with real vocals in 50 languages, returns a song link
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
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).
finished song lyrics with [Verse]/[Chorus] section tags on their own lines
ISO code of the lyrics language (ru, en, es, de…): the language you wrote the lyrics in. The server checks it against the lyrics and trusts the lyrics if they disagree. ru — the song lives on opensoundbox.ru, any other — on opensoundbox.com
music style preset (pop, rock, hiphop, rnb, country, edm, poppunk, indie, lofi, kids, ballad, chanson, lullaby, folk, jazz); custom — your own style from sound_description (no preset is mixed in). Default auto — the server picks a style from the lyrics
optional: the song title for its page
voice; default auto — picked from the lyrics
song length in seconds, in steps of 15; default 60
optional (required with style=custom): the sound in your own words, e.g. "doom metal with church organ, slow, heavy"
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http ai-song-generator https://opensoundbox.com/mcp
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).
| Argument | Type | Description |
|---|---|---|
| style | string | music style preset (pop, rock, hiphop, rnb, country, edm, poppunk, indie, lofi, kids, ballad, chanson, lullaby, folk, jazz); custom — your own style from sound_description (no preset is mixed in). Default auto — the server picks a style from the lyrics |
| title | string | optional: the song title for its page |
| voice | string | voice; default auto — picked from the lyrics |
| lyrics* | string | finished song lyrics with [Verse]/[Chorus] section tags on their own lines |
| language* | string | ISO code of the lyrics language (ru, en, es, de…): the language you wrote the lyrics in. The server checks it against the lyrics and trusts the lyrics if they disagree. ru — the song lives on opensoundbox.ru, any other — on opensoundbox.com |
| duration_seconds | integer | song length in seconds, in steps of 15; default 60 |
| sound_description | string | optional (required with style=custom): the sound in your own words, e.g. "doom metal with church organ, slow, heavy" |
{
"type": "object",
"required": [
"lyrics",
"language"
],
"properties": {
"style": {
"enum": [
"auto",
"pop",
"rock",
"hiphop",
"rnb",
"country",
"edm",
"poppunk",
"indie",
"lofi",
"kids",
"ballad",
"chanson",
"lullaby",
"folk",
"jazz",
"custom"
],
"type": "string",
"description": "music style preset (pop, rock, hiphop, rnb, country, edm, poppunk, indie, lofi, kids, ballad, chanson, lullaby, folk, jazz); custom — your own style from sound_description (no preset is mixed in). Default auto — the server picks a style from the lyrics"
},
"title": {
"type": "string",
"maxLength": 80,
"description": "optional: the song title for its page"
},
"voice": {
"enum": [
"auto",
"male",
"female",
"duet"
],
"type": "string",
"description": "voice; default auto — picked from the lyrics"
},
"lyrics": {
"type": "string",
"maxLength": 3000,
"minLength": 20,
"description": "finished song lyrics with [Verse]/[Chorus] section tags on their own lines"
},
"language": {
"enum": [
"ar",
"az",
"bg",
"bn",
"ca",
"cs",
"da",
"de",
"el",
"en",
"es",
"fa",
"fi",
"fr",
"he",
"hi",
"hr",
"ht",
"hu",
"id",
"is",
"it",
"ja",
"ko",
"la",
"lt",
"ms",
"ne",
"nl",
"no",
"pa",
"pl",
"pt",
"ro",
"ru",
"sa",
"sk",
"sr",
"sv",
"sw",
"ta",
"te",
"th",
"tl",
"tr",
"uk",
"ur",
"vi",
"yue",
"zh"
],
"type": "string",
"description": "ISO code of the lyrics language (ru, en, es, de…): the language you wrote the lyrics in. The server checks it against the lyrics and trusts the lyrics if they disagree. ru — the song lives on opensoundbox.ru, any other — on opensoundbox.com"
},
"duration_seconds": {
"type": "integer",
"maximum": 300,
"minimum": 45,
"multipleOf": 15,
"description": "song length in seconds, in steps of 15; default 60"
},
"sound_description": {
"type": "string",
"maxLength": 200,
"description": "optional (required with style=custom): the sound in your own words, e.g. \"doom metal with church organ, slow, heavy\""
}
},
"additionalProperties": false
}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.
| Argument | Type | Description |
|---|---|---|
| body | string | what you called, with which arguments, what you expected, what came back |
| kind | string | problem — works wrong; improvement — something is missing; question — something is unclear |
| tool | string | tool name; empty — about the whole server |
| title* | string | the gist in one sentence, at least 10 characters |
{
"type": "object",
"required": [
"title"
],
"properties": {
"body": {
"type": "string",
"maxLength": 2000,
"description": "what you called, with which arguments, what you expected, what came back"
},
"kind": {
"enum": [
"problem",
"improvement",
"question"
],
"type": "string",
"description": "problem — works wrong; improvement — something is missing; question — something is unclear"
},
"tool": {
"type": "string",
"description": "tool name; empty — about the whole server"
},
"title": {
"type": "string",
"maxLength": 200,
"minLength": 10,
"description": "the gist in one sentence, at least 10 characters"
}
},
"additionalProperties": false
}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.
| Argument | Type | Description |
|---|---|---|
| song_id* | string | song_id from the create_song response |
{
"type": "object",
"required": [
"song_id"
],
"properties": {
"song_id": {
"type": "string",
"pattern": "^[a-f0-9]{20}$",
"description": "song_id from the create_song response"
}
},
"additionalProperties": false
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 11, 2026.