Try MiniMax FastH3 V2 from Fastvideo →
Sign InStart Building

Task History

Click to see output list

No tasks yet

Go to Models
Music GenerationActive

Text To Song

bytencent-ailab

Song Generation 2 generates full songs with vocals and instrumentals from lyrics — supports 14 genres, reference audio cloning, and separate track output (vocal/bgm/mix).

Music GenerationText to Song
Model ID
SongGeneration 2
Provider
tencent-ailab
Updated
1775024437
wiro playground—tencent-ailab/SongGeneration 2
Reset to defaults
0 / 1
Maximum 1 audio allowed

Upload a reference audio to clone its style. If provided, caption and genre are ignored.

Comma-separated style tags (e.g. female, pop, energetic, piano). Ignored if reference audio or genre is provided.

Trigger Word(s):

Song lyrics with structure tags ([verse], [chorus], [bridge], [intro-short], [outro-short], etc.). If empty, switches to instrumental mode automatically. Max duration: 4m 30s.

Music genre. If set, caption is ignored. Default: None

Sample outputs
Updated 1775024437

# Song Generation 2

Generate full songs with vocals and instrumentals from lyrics — supports 14 genres, reference audio cloning, and separate track output (vocal/bgm/mix).

---

### Parameters

- lyrics (string, default: empty) — Song lyrics with structure tags. If empty, switches to instrumental mode automatically.

- caption (string, default: empty) — Music style description as comma-separated tags (e.g. female, pop, energetic, piano).

- audio (string, default: null) — Path to a reference audio file to clone its style.

- genre (string, default: empty) — Genre selection: Pop, Rock, Electronic, Hip-Hop, R&B/Soul, Jazz, Latin, Country, Metal, Ballad, Funk, Soundtrack, World, Auto.

- generate_type (string, default: mixed) — Output type: mixed, bgm, vocal, separate.

### Advanced

- guidance_scale (float, default: 1.5) — How closely the output follows the prompt. Higher = more faithful.

- temperature (float, default: 0.9) — Creativity level. Higher = more diverse, lower = more predictable.

### Style Control

Priority: audio > genre > caption

- If audio is provided — reference audio is used to clone the style. Caption and genre are ignored.

- If genre is provided (no audio) — predefined genre tokens are used. Caption is ignored.

- If caption is provided (no audio, no genre) — free-text description guides the generation.

- If none are provided — default generation with [Musicality-very-high] tag.

Important: Do not combine audio with caption — if both are provided, caption is silently discarded.

Example prompts

Great starting points for SongGeneration 2.

[verse] Empty streets, walking all alone Echoes of your voice inside my phone Late night thoughts keep pulling me in I wonder if you feel the way I did [chorus] I’m lost without you, can’t you see? The pieces don’t fit without you next to me Every step I take just leads me back to you I’m lost without you, what am I gonna do? [verse] Pictures fade but memories stay I’m haunted by the words I didn’t say You were the calm inside my storm Now I’m here just trying to stay warm [bridge] If you feel alone tonight Know I’m still holding tight Waiting for a sign from you [outro] I’m lost without you, I’m lost without youMusic Generation
[verse] Staring at the sunset, colors paint the sky Thoughts of you keep swirling, can't deny I know I let you down, I made mistakes But I'm here to mend the heart I didn't break [chorus] Every road you take, I'll be one step behind Every dream you chase, I'm reaching for the light You can't fight this feeling now I won't back down You know you can't deny it now I won't back down [verse] They might say I'm foolish, chasing after you But they don't feel this love the way we do My heart beats only for you, can't you see? I won't let you slip away from me [bridge] No, I won't back down, won't turn around Until you're back where you belong I'll cross the oceans wide, stand by your side Together we are strong [outro] Every road you take, I'll be one step behind Every dream you chase, love's the tie that binds You can't fight this feeling now I won't back downMusic Generation
[verse] Woke up feeling stronger than before I’ve been through battles, scars and more This heart don’t break, it only learns Watch me rise, feel the fire burn [chorus] I’ve got fire in my veins Can’t hold me down, can’t feel the chains Every word, every fight, feeds the flame I’ve got fire in my veins [verse] Doubt me now, you’ll see me fly Failure’s just fuel that keeps me alive Lightning strikes but I won’t fall I’m standing here, I’m standing tall [bridge] This is my time, this is my fight Burning brighter in the night [outro] Fire in my veins, fire in my soul You can’t stop what you can’t controlMusic Generation
[verse] Neon lights blur the city view I’m lost in thought, dreaming of you Every song plays like you’re near Your voice still lingers in my ear [chorus] I wanna fade into you Let this world disappear too Every second feels brand new When I fade into you [verse] Time slows down when you’re in my mind All the noise just leaves me behind Floating through this midnight blue All I want is to be with you [bridge] Colors melt, shadows break Hearts collide, we can’t fake [outro] Fade into you… fade into youMusic Generation

API quick start

Run SongGeneration 2 with a single API call.

POST https://api.wiro.ai/v1/Run/tencent-ailab/songgeneration-2
{
  "prompt": "[verse]\nBright lights flashing in the cit…",
  "caption": "female, slow, piano",
  "temperature": 0.8,
  "inputAudio": "https://your-cdn.com/input.mp3"
}
curl
curl -X POST "https://api.wiro.ai/v1/Run/tencent-ailab/songgeneration-2" \
  -H "Content-Type: application/json" \
  -H "x-api-key: YOUR_WIRO_API_KEY" \
  --data-binary @- <<'JSON'
{
  "prompt": "[verse]\nBright lights flashing in the cit…",
  "caption": "female, slow, piano",
  "temperature": 0.8,
  "inputAudio": "https://your-cdn.com/input.mp3"
}
JSON
View full API docs