Claude visitors: new accounts receive $1.00 in bonus API credit within 30 days. One per person; usage credits only.
Use Suno in WorkBuddy.
Suno generates full songs — vocals, instruments, and mixing — from a text prompt or exact lyrics. Versions v4 through v5.5 are available through RunAPI, which provides API access since Suno has no official public API. Add RunAPI as an MCP server once, and the WorkBuddy agent handles the async task and hands back the finished audio URL.
Using the runapi MCP server, generate a song with Suno.
Requirements:
- Call the Suno text_to_music tool exposed by the runapi MCP server.
- Set model to "suno-v5.5".
- Set vocal_mode to "auto_lyrics" so the lyrics are written from my brief.
- Prompt: an upbeat indie pop track about coding late at night,
warm synths and acoustic guitar, female vocals.
- The task is async — keep polling until the status is "completed",
then give me the audio URL.
{
"mcp_servers": {
"runapi": {
"url": "https://runapi.ai/mcp",
"transport": "streamable_http",
"headers": {
"Authorization": "Bearer $RUNAPI_API_KEY"
}
}
}
}
{
"task_id": "tsk_abc123",
"status": "completed",
"model": "suno-v5.5",
"output": {
"audio_url": "https://media.runapi.ai/outputs/tsk_abc123.mp3",
"title": "Midnight Compile",
"duration_seconds": 187
}
}
Use Suno in WorkBuddy in three steps
Add RunAPI as an MCP server
Set RUNAPI_API_KEY in the environment that launches WorkBuddy, then register an MCP server named runapi pointing at https://runapi.ai/mcp over streamable HTTP. Suno appears as a callable music tool alongside every other RunAPI model — no separate music service to wire up.
export RUNAPI_API_KEY=runapi_xxx
# MCP server: runapi → https://runapi.ai/mcp
Describe the song to the agent
Tell WorkBuddy what you want in plain language and name the mode. Use auto_lyrics with a prompt for AI-written lyrics, exact_lyrics with lyrics/style/title for your own words, or instrumental with style/title for no vocals. The agent maps your brief onto the Suno tool call.
vocal_mode: auto_lyrics
Let the agent poll and collect the audio
Song generation is async and takes 30 seconds to several minutes depending on version. The workbench agent polls the task until the status is completed, then posts the output audio URL back into the conversation — you never touch a task_id yourself.
"status": "completed"
Suno text_to_music parameters
| Parameter | Type | Description |
|---|---|---|
model |
string |
Required. suno-v4, suno-v4.5, suno-v4.5-all, suno-v4.5-plus, suno-v5, or suno-v5.5. |
vocal_mode |
string |
Required. auto_lyrics (AI writes lyrics from prompt), exact_lyrics (you provide lyrics/style/title), or instrumental (no vocals, requires style/title). |
prompt |
string |
Song brief for auto_lyrics mode. Describe genre, mood, tempo, and subject. Forbidden in exact_lyrics and instrumental modes. |
lyrics |
string |
Exact lyrics to sing. Required for exact_lyrics mode. Forbidden in auto_lyrics and instrumental modes. |
style |
string |
Music style description, e.g. lo-fi hip hop, 80s synthwave. Required for exact_lyrics and instrumental modes. |
vocal_gender |
string |
Optional. male or female. |
negative_tags |
string |
Optional. Styles to avoid, e.g. heavy metal, screaming. |
What is Suno on WorkBuddy?
Suno is a text-to-music AI that generates complete songs -- vocals, instruments, and mixing -- from a text prompt or your own lyrics. It works as a songwriting sketchpad where you describe the genre, mood, and tempo, and get back a full track. WorkBuddy reaches it through the RunAPI MCP server since Suno has no official public API, giving the workbench agent programmatic access to versions v4 through v5.5 with the same key it uses for chat and images.
Suno use cases
Background music for YouTube and social media
Ask the workbench agent for original background tracks by describing the mood and genre. No licensing fees, no royalty issues -- the track is generated fresh for your content and the URL lands back in WorkBuddy.
Hearing lyrics as a full song
Lyric writers can paste their words into WorkBuddy and ask for exact_lyrics mode with a style description, hearing them performed as a complete song — a production demo before studio time.
Podcast intros and outros
Create instrumental intro and outro music matched to a podcast's tone by specifying genre, mood, and duration. Have the agent generate several variations in one conversation and pick the best fit.
Suno + WorkBuddy questions
Be specific about genre, mood, tempo, and instrumentation in your brief to WorkBuddy. For example, "upbeat 120 BPM indie pop with acoustic guitar and warm synths" works better than "happy song." Ask the agent to pass negative_tags to exclude unwanted elements such as heavy metal or screaming.
suno-v5.5 is the latest and produces the highest quality output with better vocal clarity and mixing. suno-v4 and suno-v4.5 are cheaper and faster for draft iterations. All versions sit behind the same runapi MCP server, so switching is just naming a different version in your prompt.
No. Suno tasks are async, but the workbench agent handles the lifecycle — it creates the task through the MCP tool, polls until the status is completed, and posts the audio URL back into the conversation. You just describe the song and wait.
Suno does not offer a public API. RunAPI provides programmatic access to Suno v4 through v5.5 through the same API key and task lifecycle used for all other RunAPI models. No Suno account or separate credentials needed.
Yes. Ask for vocal_gender male or female, and use negative_tags to exclude unwanted styles. For finer control, create a persona through the personas endpoint and pass the returned persona_id with persona_type set to voice or style.
WorkBuddy general setup
Not connected yet? Start with the RunAPI MCP setup guide for WorkBuddy.
WorkBuddy setup guide →Try Suno in WorkBuddy today.
Get a free RunAPI key, add the MCP server to WorkBuddy, and describe a song — the workbench agent returns a full track with vocals, instruments, and mixing.