io.github.AceDataCloud/mcp-producer

Upload an external audio file for use in subsequent operations. Uploads audio from a URL so it can be used with actions like extend, cover, variation, swap_vocals, and swap_instrumentals. Use this when: - You have your own music you want to process with Producer - You want to use an external audio as a base for operations - You need to import audio into Producer's system After uploading, use the returned audio_id with other Producer tools. Returns: Upload result with audio ID for use in subsequent operations.

Generate a video for a previously generated song. Creates a video with visualizations for a generated audio track. Useful for sharing on social media or video platforms. Use this when: - You want a video version of a generated song - You need to share the song on video platforms - You want a visual representation of the audio Returns: Task ID and video generation information.

Get the lossless WAV format of a generated song. Converts the song to high-quality uncompressed WAV format. WAV files are larger but have no quality loss compared to MP3. Use this when: - You need a lossless audio format for production - You want the highest quality audio output - You need uncompressed audio for further processing Returns: Task ID and WAV audio information.

Generate song lyrics from a text prompt. Creates structured lyrics with proper song sections (Verse, Chorus, Bridge, etc.) based on your description. The generated lyrics are formatted and ready to use with producer_generate_custom_music. Use this when: - You need lyrics but don't want to write them yourself - You want AI-generated lyrics for a specific theme or mood - You need properly structured lyrics with section markers The output includes section markers like [Verse], [Chorus], [Bridge] that Producer's music generation understands. Returns: Generated lyrics with title, status, and formatted text with section markers.

List all available Producer/FUZZ models and their capabilities. Shows all available model versions with their features and recommended use cases. Use this to understand which model to choose for your music generation. Returns: Table of all models with their version and features.

List all available Producer API actions and corresponding tools. Reference guide for what each action does and which tool to use. Helpful for understanding the full capabilities of the Producer MCP. Returns: Categorized list of all actions and their corresponding tools.

Get guidance on formatting lyrics for Producer music generation. Shows how to structure lyrics with section markers for best results. Following this format helps Producer understand the song structure and generate appropriate melodies for each section. Returns: Complete guide with section markers, examples, and tips.

Generate AI music from a text prompt using Producer/Riffusion. This is the simplest way to create music - just describe what you want and Producer will automatically generate appropriate lyrics, melody, style, and arrangement. Use this when: - You want quick music generation with minimal input - You don't have specific lyrics in mind - You want the AI to be creative with the arrangement For full control over lyrics and style, use producer_generate_custom_music instead. Returns: Task ID and generated audio information including URLs, title, lyrics, and duration.

Generate AI music with full control over lyrics, title, and style. This gives you complete creative control over the song. You provide the lyrics with section markers, and Producer generates the melody and arrangement. Use this when: - You have specific lyrics you want to use - You want precise control over the music style - You need a specific song title For quick generation without writing lyrics, use producer_generate_music instead. Returns: Task ID and generated audio information including URLs, title, lyrics, and duration.

Extend an existing song from a specific timestamp with new content. This allows you to continue a previously generated song, adding new sections like additional verses, a bridge, or an outro. Use this when: - A generated song is too short and you want to add more - You want to add a bridge or outro to an existing song - You're building a longer song piece by piece Returns: Task ID and the extended audio information.

Create a cover or remix version of an existing song in a different style. This generates a new version of a song with a different arrangement, genre, or mood while keeping the core melody and lyrics. Use this when: - You want to hear a song in a different genre - You want an acoustic/unplugged version of an electronic song - You want to remix a song with a different vibe Returns: Task ID and the cover audio information.

Create a variation of an existing song with modifications. Generates a new version of the song with subtle changes to the arrangement, melody, or style while keeping the overall structure similar. Use this when: - You like a song but want a slightly different version - You want to explore different interpretations of the same idea - You need multiple takes of a similar song Returns: Task ID and the variation audio information.

Swap the vocals of one song with vocals from another song. Requests vocal swapping for the provided audio. Use this when: - You want to combine vocals from one song with instrumentals from another - You want to hear how different vocals sound over the same beat - You're creating a vocal mashup Returns: Task ID and the swapped audio information.

Swap the instrumental track of one song with instrumentals from another. Requests instrumental swapping for the provided audio. Use this when: - You want to combine instrumentals from one song with vocals from another - You want to hear how the same vocals sound over different music - You're creating an instrumental mashup Returns: Task ID and the swapped audio information.

Replace a specific time range in a song with new generated content. Re-generates a portion of a song between the specified start and end times, keeping the rest of the song unchanged. Great for fixing sections you don't like. Use this when: - A specific section of a song needs improvement - You want to change lyrics in the middle of a song - You want to replace a verse or chorus with something different Returns: Task ID and the updated audio information.

Separate a song into individual stems (vocals and instruments). Splits the audio into separate tracks for vocals and instrumentals, useful for remixing, karaoke, or isolating specific parts. Use this when: - You want to separate vocals from instrumentals - You need individual stem tracks for mixing - You want to create a karaoke version Returns: Task ID and stem separation results with individual track URLs.

Query the status and result of a music generation task. Use this to check if a generation is complete and retrieve the resulting audio URLs, titles, lyrics, and other metadata. Use this when: - You want to check if a generation has completed - You need to retrieve audio URLs from a previous generation - You want to get the full details of a generated song Task states: - 'pending': Generation is still in progress — KEEP POLLING - 'processing': Generation is being processed — KEEP POLLING - 'complete': Generation finished successfully — this is the ONLY state that means done - 'failed': Generation failed (check error message) CRITICAL: During the 'pending' state, the response may already contain intermediate audio_url values (streaming preview URLs). These are NOT final results. You MUST check the 'state' field — only present the results to the user when state is 'complete' and success is true. Do NOT stop polling just because audio_url is non-empty. Returns: Task status and generated audio information including URLs, title, lyrics, and task timing metadata.

Query multiple music generation tasks at once. Efficiently check the status of multiple tasks in a single request. More efficient than calling producer_get_task multiple times. Use this when: - You have multiple pending generations to check - You want to get status of several songs at once - You're tracking a batch of generations CRITICAL: Same as producer_get_task — only consider a task complete when its state is 'complete' and success is true. Intermediate audio_url values during 'pending' state are streaming previews, NOT final results. Returns: Status and audio information for all queried tasks.