Suno · Audio & Music

Hermes Agent x Suno

Suno is an AI music generation platform that creates original songs — vocals, instruments, and lyrics — from text descriptions. Through RunAPI, all Suno versions share a single API key with per-call billing.

9 variants from $0.01 / call Commercial OK
Get API Key View Hermes Agent Docs

Prerequisite: npx runapi mcp install

Prompt

Prompt models

Use suno-v4 when it matches the task: Improved coherence and frequency range, 4-min cap.

You have access to RunAPI task tools for Suno.

Available Suno models:
- suno-v4: Improved coherence and frequency range, 4-min cap
  endpoints: /api/v1/suno/stitch_audio, /api/v1/suno/extend_music, /api/v1/suno/create_mashup, /api/v1/suno/add_samples, /api/v1/suno/cover_audio, /api/v1/suno/inspire_music, /api/v1/suno/text_to_music, /api/v1/suno/remaster_audio
  request fields: model, vocal_mode, prompt, persona_id, persona_type
- suno-v4.5: 8-min first-generation, 25% fewer genre errors, 40% better vocals
  endpoints: /api/v1/suno/remaster_audio, /api/v1/suno/create_mashup, /api/v1/suno/extend_music, /api/v1/suno/add_samples, /api/v1/suno/stitch_audio, /api/v1/suno/inspire_music, /api/v1/suno/cover_audio, /api/v1/suno/text_to_music
  request fields: model, vocal_mode, prompt, persona_id, persona_type
- suno-v4.5-all: All v4.5 styles and modes unlocked without subscription gating
  endpoints: /api/v1/suno/extend_music, /api/v1/suno/create_mashup, /api/v1/suno/cover_audio, /api/v1/suno/text_to_music
  request fields: model, vocal_mode, prompt, persona_id, persona_type
- suno-v4.5-plus: Enhanced quality tier within the v4.5 architecture
  endpoints: /api/v1/suno/cover_audio, /api/v1/suno/remaster_audio, /api/v1/suno/add_samples, /api/v1/suno/create_mashup, /api/v1/suno/stitch_audio, /api/v1/suno/text_to_music, /api/v1/suno/inspire_music, /api/v1/suno/extend_music, /api/v1/suno/add_instrumental, /api/v1/suno/add_vocals
  request fields: model, vocal_mode, prompt, persona_id, persona_type
- suno-v5: CD-quality audio, up to 8 min per generation
  endpoints: /api/v1/suno/remaster_audio, /api/v1/suno/text_to_sound, /api/v1/suno/add_samples, /api/v1/suno/add_instrumental, /api/v1/suno/create_mashup, /api/v1/suno/stitch_audio, /api/v1/suno/cover_audio, /api/v1/suno/inspire_music, /api/v1/suno/text_to_music, /api/v1/suno/extend_music, /api/v1/suno/add_vocals
  request fields: model, vocal_mode, prompt, persona_id, persona_type
- suno-v5.5: Up to 8 min per generation, voice cloning and style training
  endpoints: /api/v1/suno/text_to_sound, /api/v1/suno/add_samples, /api/v1/suno/create_mashup, /api/v1/suno/stitch_audio, /api/v1/suno/text_to_music, /api/v1/suno/cover_audio, /api/v1/suno/inspire_music, /api/v1/suno/extend_music, /api/v1/suno/add_instrumental, /api/v1/suno/remaster_audio
  request fields: model, vocal_mode, prompt, persona_id, persona_type
- suno-v6: suno-v6
  endpoints: /api/v1/suno/create_mashup, /api/v1/suno/text_to_music, /api/v1/suno/cover_audio, /api/v1/suno/extend_music
  request fields: model, vocal_mode, prompt, persona_id, persona_type
- suno-v6-mini: suno-v6-mini
  endpoints: /api/v1/suno/cover_audio, /api/v1/suno/create_mashup, /api/v1/suno/text_to_music, /api/v1/suno/extend_music
  request fields: model, vocal_mode, prompt, persona_id, persona_type
- suno-v6-wild: suno-v6-wild
  endpoints: /api/v1/suno/create_mashup, /api/v1/suno/cover_audio, /api/v1/suno/text_to_music, /api/v1/suno/extend_music
  request fields: model, vocal_mode, prompt, persona_id, persona_type

Use the model ID and endpoint that match the user's request.
Example prompt: Write a lo-fi chill beat with soft piano, vinyl crackle, and a gentle bass line, 2 minutes long.
/api/v1/suno/stitch_audio: Submit the task, poll for its status, then verify the completed output. POST /api/v1/suno/stitch_audio and save the returned Task id.
GET /api/v1/suno/stitch_audio/<task-id> until status is completed or failed.
Verify the completed response contains the endpoint-specific output documented in the API reference.
/api/v1/suno/extend_music: Submit the task, poll for its status, then verify the completed output. POST /api/v1/suno/extend_music and save the returned Task id.
GET /api/v1/suno/extend_music/<task-id> until status is completed or failed.
Verify the completed response contains the endpoint-specific output documented in the API reference.
/api/v1/suno/create_mashup: Submit the task, poll for its status, then verify the completed output. POST /api/v1/suno/create_mashup and save the returned Task id.
GET /api/v1/suno/create_mashup/<task-id> until status is completed or failed.
Verify the completed response contains the endpoint-specific output documented in the API reference.
/api/v1/suno/add_samples: Submit the task, poll for its status, then verify the completed output. POST /api/v1/suno/add_samples and save the returned Task id.
GET /api/v1/suno/add_samples/<task-id> until status is completed or failed.
Verify the completed response contains the endpoint-specific output documented in the API reference.
/api/v1/suno/cover_audio: Submit the task, poll for its status, then verify the completed output. POST /api/v1/suno/cover_audio and save the returned Task id.
GET /api/v1/suno/cover_audio/<task-id> until status is completed or failed.
Verify the completed response contains the endpoint-specific output documented in the API reference.
/api/v1/suno/inspire_music: Submit the task, poll for its status, then verify the completed output. POST /api/v1/suno/inspire_music and save the returned Task id.
GET /api/v1/suno/inspire_music/<task-id> until status is completed or failed.
Verify the completed response contains the endpoint-specific output documented in the API reference.
/api/v1/suno/text_to_music: Submit the task, poll for its status, then verify the completed output. POST /api/v1/suno/text_to_music and save the returned Task id.
GET /api/v1/suno/text_to_music/<task-id> until status is completed or failed.
Verify the completed response contains the endpoint-specific output documented in the API reference.
/api/v1/suno/remaster_audio: Submit the task, poll for its status, then verify the completed output. POST /api/v1/suno/remaster_audio and save the returned Task id.
GET /api/v1/suno/remaster_audio/<task-id> until status is completed or failed.
Verify the completed response contains the endpoint-specific output documented in the API reference.
/api/v1/suno/add_instrumental: Submit the task, poll for its status, then verify the completed output. POST /api/v1/suno/add_instrumental and save the returned Task id.
GET /api/v1/suno/add_instrumental/<task-id> until status is completed or failed.
Verify the completed response contains the endpoint-specific output documented in the API reference.
/api/v1/suno/add_vocals: Submit the task, poll for its status, then verify the completed output. POST /api/v1/suno/add_vocals and save the returned Task id.
GET /api/v1/suno/add_vocals/<task-id> until status is completed or failed.
Verify the completed response contains the endpoint-specific output documented in the API reference.
/api/v1/suno/text_to_sound: Submit the task, poll for its status, then verify the completed output. POST /api/v1/suno/text_to_sound and save the returned Task id.
GET /api/v1/suno/text_to_sound/<task-id> until status is completed or failed.
Verify the completed response contains the endpoint-specific output documented in the API reference.

Public Versions and Endpoints

Suno V6 is now available. Requests using older model IDs (v3.5–v5.5) are automatically routed to V6 or V6 Mini. Pricing remains unchanged.
Model ID Endpoints Price Catalog
suno-v4
/api/v1/suno/stitch_audio /api/v1/suno/extend_music /api/v1/suno/create_mashup /api/v1/suno/add_samples /api/v1/suno/cover_audio /api/v1/suno/inspire_music /api/v1/suno/text_to_music /api/v1/suno/remaster_audio
$0.01 / call Model detail
suno-v4.5
/api/v1/suno/remaster_audio /api/v1/suno/create_mashup /api/v1/suno/extend_music /api/v1/suno/add_samples /api/v1/suno/stitch_audio /api/v1/suno/inspire_music /api/v1/suno/cover_audio /api/v1/suno/text_to_music
$0.01 / call Model detail
suno-v4.5-all
/api/v1/suno/extend_music /api/v1/suno/create_mashup /api/v1/suno/cover_audio /api/v1/suno/text_to_music
$0.12 / call Model detail
suno-v4.5-plus
/api/v1/suno/cover_audio /api/v1/suno/remaster_audio /api/v1/suno/add_samples /api/v1/suno/create_mashup /api/v1/suno/stitch_audio /api/v1/suno/text_to_music /api/v1/suno/inspire_music /api/v1/suno/extend_music /api/v1/suno/add_instrumental /api/v1/suno/add_vocals
$0.01 / call Model detail
suno-v5
/api/v1/suno/remaster_audio /api/v1/suno/text_to_sound /api/v1/suno/add_samples /api/v1/suno/add_instrumental /api/v1/suno/create_mashup /api/v1/suno/stitch_audio /api/v1/suno/cover_audio /api/v1/suno/inspire_music /api/v1/suno/text_to_music /api/v1/suno/extend_music /api/v1/suno/add_vocals
$0.01 / call Model detail
suno-v5.5
/api/v1/suno/text_to_sound /api/v1/suno/add_samples /api/v1/suno/create_mashup /api/v1/suno/stitch_audio /api/v1/suno/text_to_music /api/v1/suno/cover_audio /api/v1/suno/inspire_music /api/v1/suno/extend_music /api/v1/suno/add_instrumental /api/v1/suno/remaster_audio
$0.01 / call Model detail
suno-v6
/api/v1/suno/create_mashup /api/v1/suno/text_to_music /api/v1/suno/cover_audio /api/v1/suno/extend_music
$0.12 / call Model detail
suno-v6-mini
/api/v1/suno/cover_audio /api/v1/suno/create_mashup /api/v1/suno/text_to_music /api/v1/suno/extend_music
$0.12 / call Model detail
suno-v6-wild
/api/v1/suno/create_mashup /api/v1/suno/cover_audio /api/v1/suno/text_to_music /api/v1/suno/extend_music
$0.12 / call Model detail

Verify

Poll until the task reaches a terminal status

Select <model-id> to generate verification commands.

Configuration

Guide endpoint: <endpoint>

Select <model-id> to generate a request with the endpoint's public input contract.

Additional operations

These operations do not use a model ID.

  • /api/v1/suno/get_timestamped_lyrics
  • /api/v1/suno/separate_audio_stems
  • /api/v1/suno/generate_artwork
  • /api/v1/suno/generate_persona
  • /api/v1/suno/generate_midi
  • /api/v1/suno/regenerate_validation_phrase
  • /api/v1/suno/generate_voice
  • /api/v1/suno/boost_style
  • /api/v1/suno/check_voice
  • /api/v1/suno/voice_to_validation_phrase
  • /api/v1/suno/convert_audio
  • /api/v1/suno/visualize_music
  • /api/v1/suno/generate_lyrics
  • /api/v1/suno/blend_lyrics
  • /api/v1/suno/replace_section
How it works

Get Started in 3 Steps

  1. Choose a model ID

    Select a public catalog model ID and review its endpoint and current starting price.

  2. Configure RunAPI

    Set RUNAPI_API_KEY before making the endpoint request.

  3. Verify the result

    For asynchronous endpoints, poll the same endpoint until the Task reaches a terminal status.

What to Build with Hermes Agent + Suno

  • Songwriting sketchpad

    Describe a song concept with genre, mood, tempo, and subject, and get a demo track back to iterate on before studio production.

  • Covers in new styles

    Restyle an existing track by changing its genre, instrumentation, or mood while keeping the core melody and structure.

  • Complete audiovisual content pipelines

    Chain Suno with video models in a Hermes Agent workflow to create footage and a matching original soundtrack.

Why Use Suno Through RunAPI + Hermes Agent

  • 9 variants, one API key

    Use one RunAPI connection to choose among the live model variants without changing your integration.

  • Clear usage pricing

    See current catalog pricing before you send a request, with no subscription or minimum spend required.

  • Automatic task workflows

    Submit, poll, and collect asynchronous results through a consistent task workflow without writing manual polling code.

Hermes Agent + Suno Questions

How do I configure Suno in Hermes Agent?

Use the same RunAPI provider you set up for chat. It handles chat, image, video, and music endpoints, so Suno needs no separate configuration.

Can I generate instrumental tracks without vocals?

Yes. Suno supports instrumental generation. The request parameters on this page show which fields apply to instrumental mode, and the API returns a validation error if conflicting fields are sent.

Can Hermes Agent chain Suno with video models?

Yes. Hermes Agent can generate video with a video model, then create a matching soundtrack with Suno in the same workflow.

Which model ID should I use?

Choose a public model ID from the version table. Each ID exposes the endpoints shown for that version.

Does this guide configure a chat model?

No. This Model Line uses the endpoint workflow shown here and is not presented as an agent chat model.

Start using Suno with Hermes Agent

Get API Key Read Quickstart

Building with a team?

We're here to help with enterprise setup, integrations, and technical questions.

Contact Us