Mureka 9.5 Lyrics to Song API
https://api.hiapi.ai /v1/tasks Image, video, and audio models are called through theUnified Async API POST /v1/tasks endpoint; only the input fields differ (see input parameters below).
Model summary
| Model name | mureka-9.5/lyrics-to-song |
|---|---|
| Type | Audio generation (lyrics to song) |
| Endpoint | POST /v1/tasks |
| Pricing | See HiAPI Pricing |
Mureka 9.5 lyrics-to-song turns complete lyrics into a finished vocal song, with optional direction for genre, mood, arrangement, and lead vocal gender.
Production guidance
- For production, pass callback.url at the top level of the request body so HiAPI can notify your service when the task reaches a terminal state.
- GET /v1/tasks/:id is better for local debugging, low-volume jobs, or fallback reconciliation if a callback is missed.
- Use callback.when=final. Both success and fail are terminal states, so your service should deduplicate by taskId.
Best suited for
The lyrics are settled and only the vocal performance, harmonies, and arrangement remain.
lyricsUse the prompt to add genre, mood, instruments, and tempo that fit a short-video intro, brand song, or demo.
promptSet gender when the lead vocal must be female or male, keeping a character or song series consistent.
genderRequest parameters
model string required Fixed value mureka-9.5/lyrics-to-song.
input object required Business parameters. Put lyrics-to-song inputs here.
lyrics string required Complete lyrics to sing, 1–5,000 characters. Keep line breaks and the verse-chorus order so the model can organize the performance and repeated sections.
prompt string optional Optional style and arrangement direction, 1–2,000 characters: genre, mood, instruments, tempo, and vocal character. It does not replace the lyrics; it shapes the music.
gender enum optional Lead vocal gender preference: female or male. Omit to let the model decide from the lyrics and style.
callback object optional Optional callback configuration. When set, HiAPI notifies your service when the task reaches a terminal state.
url string required Required when callback is set; HTTPS URL that receives terminal task notifications.
when enum optional Callback trigger timing. Use final.
Example requests
A full English verse-and-chorus lyric with a warm indie-pop direction and a female lead vocal.
{
"model": "mureka-9.5/lyrics-to-song",
"input": {
"lyrics": "[Verse 1]\nCity lights are waking up\nEvery window starts to glow\nWe were chasing something small\nDown the streets we used to know\n[Chorus]\nWe keep moving through the night\nEvery shadow turns to gold\nHold on tight, we are wide awake\nThis is all we need to hold",
"prompt": "Warm indie-pop song with a bright female lead vocal, chiming guitars, steady live drums and a wide sing-along chorus, hopeful late-night mood.",
"gender": "female"
}
}Getting the result
- A successful submission returns a taskId immediately; it does not wait for generation.
- In production, prefer the callback.url terminal notification; poll GET /v1/tasks/:id for local debugging.
- When status=success, find the type=audio entry in output and download the audio from its url.
- If status=fail, correct the request using the returned error instead of retrying the same invalid input.
FAQ
What does the lyrics-to-song route require?
lyrics are required, 1–5,000 characters. prompt and gender are optional and add style direction and a lead vocal gender preference.
Can I provide only a description and let the model write the lyrics?
The Mureka 9.5 routes on HiAPI cover lyrics-to-song and instrumental only; automatic lyric writing is not offered. Use another music model when you need automatic lyrics.
Does the prompt replace the lyrics?
No. With lyrics present, the prompt only shapes genre, instruments, tempo, and vocal character; the sung text still comes from lyrics.
Can I upload a reference track, clone a voice, or provide a melody?
The current route does not accept reference tracks, voice cloning, or melody uploads. It accepts lyrics, an optional style direction, and vocal gender.
How is it billed?
Billing is a fixed charge per successful generation, independent of lyric length and output duration. See the live pricing page for the current rate. View pricing