chirp-v5 is a Suno V5 music creation model, suitable for turning theme descriptions or existing lyrics into songs, as well as for instrumental music creation. It offers both inspiration and custom modes, allowing creators to separately control lyrics, titles, and musical styles, while exploring different expressions through vocal preferences, style influence, and experimental adjustments. It is suitable for song demos, content soundtracks, and existing V5 creation workflows.
Submit requests to the public API at api.acedata.cloud using the documented parameters, then use the results in your application.
api.acedata.cloudchirp-v5Input parameters and result formats vary by service. Use the public API for this model and follow its guide for generation, task retrieval and editing operations.
Clarify capacity, inputs and outputs, and invocation methods before selecting a model.
The values above are the input ranges for this platform's creation interface. Desired duration and expression controls do not guarantee the final output.
Learn what chirp-v5 can bring to your work.
Inspiration mode is suited to creative starting points when lyrics have not yet been written. Use a piece of text to describe the song's theme, genre, and mood, then choose whether to generate instrumental music to begin exploring musical directions. Keep the main intent focused in the prompt, such as summer travel, upbeat pop, and a warm atmosphere, and avoid stacking contradictory requirements.
Custom mode lets lyrics, titles, and styles each serve their own purpose: lyrics organize the narrative and sections, while style describes the genre, instruments, and overall sound. Existing copy can be entered directly as lyrics; when you only have a writing direction, you can use lyric_prompt to guide lyric creation. More generous text space is suitable for expressing multiple verses, choruses, and bridges.
chirp-v5 lets you set preferences for male or female vocals and adjust style influence and weirdness in custom mode. The former guides how closely the style is followed, while the latter explores more experimental expression. In actual creation, keep the same lyrics, adjust control values one at a time, and then listen, avoiding changing all conditions at once and making results difficult to evaluate.
Start with specific tasks to find where the model can be effective.
Enter existing lyrics, a song title, and a target style into custom mode to create song demos for listening and discussion. For example, try folk and electronic pop around the same chorus, then compare lyric delivery and overall mood. When delivering, save the audio and song ID to help the team record selection results and subsequent creative directions.
Describe the desired mood and genre for travel videos, program intros, or podcast transitions, choose instrumental creation, and obtain audio that can be auditioned in editing. If you have a target length, you can set the desired duration in custom generation; the final result should still be trimmed and transitions arranged according to the actual audio, rather than treating the requested length as a precise timeline.
When an existing song needs remastering options, V5's remaster workflow requires selecting variation_category, and high, normal, or subtle can be used to indicate the degree of change. Keep the original track and listen to each remastered result separately to compare which changes suit the project; deliver candidate audio and degree records rather than replacing the original version by default.
Choose based on task complexity, input materials, and expected results.
Compared with chirp-v4, chirp-v5 expands custom lyric input from 3000 characters to 5000 characters and style descriptions from 200 characters to 1000 characters, making it better suited for projects with longer lyrics or detailed arrangement intentions. If you already have a V4.5 or V4.5+ workflow, text limits are not a unique advantage of V5; decide whether to switch based on actual listening results.
chirp-v5 and chirp-v5-5 are different model types for invocation and should not be treated as the same version merely because their names are similar. If you already have V5 works and parameter templates, you can continue managing creation with V5; when preparing to try V5.5, it is recommended to use the same lyrics and style for comparative listening. Both have the same lyric and style input limits, so it is not advisable to judge audio quality solely by these numbers.
Arrange the inputs first, then connect them to the corresponding application workflow.
Prepare the video theme, primary emotions, and rhythm changes, and specify whether you need a vocal song or instrumental music.
Explicitly select chirp-v5. Use prompt for theme creation; for custom creation, organize lyric, style, and title according to this model's limits. Save task_id, retrieve audio_url after waiting for the completed result, and archive it together with the work ID and creation settings.
Design tasks directly from the following inputs and acceptance priorities.
Generate both restrained and passionate versions for the same theme, keeping all other fields consistent and explicitly specifying chirp-v5.
Compare the beat, transitions, and degree to which the music overwhelms the visuals during playback; record the actual duration and reasons for selection. Prompts do not guarantee precise synchronization with edit points.
Before formal use, understand the output quality and capability scope.
Answers to common questions when using chirp-v5.
When you only have a theme and musical direction, use the default inspiration mode and fill in prompt; when you already have lyrics, set custom=true and provide lyric, title, and style separately. If no lyrics are provided in custom mode, you can also use lyric_prompt to describe the lyric content you want to create.
You can use the instrumental creation method. Set instrumental in inspiration mode, and use prompts to describe the genre, mood, and desired instrumental sound. When used for video or podcasts, it is recommended to first listen to whether the music suits the visuals and narration, then edit and arrange it according to the actual finished length.
No. Custom generation accepts integer desired values from 10—360 seconds, but this value is only a creative preference, not a hard length constraint. Use the returned duration and actual playback content as the reference; if the project requires an exact length, allow time for selection and audio editing.
When using remaster, V5 requires variation_category, with available options high, normal, and subtle. It is used to select the remaster variation level and is not equivalent to the generation diversity parameter. It is recommended to keep the original audio and compare results at different levels before deciding which version to use.
Submit a request to POST /suno/audios and specify model=chirp-v5. Set async=true to first obtain task_id, then query the task result; you can also provide callback_url to receive callbacks. After completion, read the song status, audio_url, and actual duration, and save the required audio.
Choose a development approach or application suited to this model and follow its setup guide.
↗Python SDK Integration Guide
SDK installation, authentication and examples↗TypeScript SDK Integration Guide
SDK installation, authentication and examples
↗
↗
↗Pricing
$0.0532· per generation
You pay$71,316for 750,000 credits · $0.0951 / credits46% OFF
You're billed in credits. Pick a top-up tier to see its per-credit rate — the larger the top-up, the cheaper each credit.
This is only a basic call example. See the full docs for more parameters and advanced usage.
View Docs