AudioLDM 2

Free.ai (self-hosted) · music · ~5000 tokens per track · 4.0 Lọ́wọ́lọ́wọ́ 4 Àwọn òǹlò tí a fi pamọ́

Àwọn àwọn

Àwọn àyọkà (tí a yan)

Ìgbà ìtàn

Àwọn àwọn

~5000 tokens per track

AudioLDM 2 ni an Àwọn àwọn tí Haohe Liu kọ̀. Ó ní ìmọ́ nínú Music generation from text. Ààyè àìṣàfilọ́lẹ̀ fún ara rẹ̀ ní àwọn GPUs Free.ai — láàyè láti pàtó àwọn ààyè àìṣàfilọ́lẹ̀ rẹ̀ ní ọjọ́ (5,000 ààyè fún àkọlé kan). Ti fi silẹ labẹ Apache 2.0 — lilo iṣowo ti gba laaye lori Free.ai.

Lò nípa API

API REST tí a bá fẹ́ OpenAI. Ṣẹ̀dá bọ́tìnì náà láti pé ìṣàmúlò-ètò yìí nínú àwọn ìsàlẹ̀-ètò.

curl -X POST https://api.free.ai/v1/music/generate/ \
  -H "Authorization: Bearer sk-free-..." \
  -H "Content-Type: application/json" \
  -d '{"model":"audioldm2","prompt":"your prompt here"}'

Àwọn Àkọsílẹ̀ Gba àwọn àwọn àmì-ìwé API

Àwọn ìṣàmúlò-ètò ìsàlẹ̀-ètò

ACE-Step Music

DiffRhythm

ElevenLabs Music

Lyria 3 Music

MusicGen (MG-Medium)

Stable Audio

Wá gbogbo àwọn ìṣàmúlò-ètò →

Àwọn Àtòjọ-ẹ̀yàn

AudioLDM 2 kọ̀ọ̀kan àwọn ìraǹrọ̀ ìṣàfarawé (ati ní àwọn iǹinà àwọn, àwọn ìgbàgbọ̀) láti inú àkọ́lé àkọ́kọ́. Ṣàfihàn àwọn ìrànwọ́, ìṣàfihàn, àwọn ìraǹrọ̀, tàbí BPM àti AudioLDM 2 ń fi àkọ́kọ́ àwòrán tí a tí parì pamọ́.

10 si 60 àwọn ìṣísẹ̀ fún ìṣàfihàn kan nípa ìpéwọ̀n. Fún àwọn àwọn ààyè tí o jú lọ, kọ̀ọ̀kan àwọn ìṣàfihàn lọ́wọ́lọ́wọ́ láti inú /music/stitch/ tàbí kọ̀ọ̀kan àwọn àwọn ààyè 30-iségétì àti ìpàdá.

Àwọn ináǹẹ̀tì kan náà ń fi àwọn àwòrán pamọ́ láti inú àwọn àyọkà ìtàn tí o fi pamọ́ (pàtó àwòrán nínú àwọn àwọn fọọmu); àwọn mìíràn ní àwọn àwòrán-ìṣàmúlò-ètò. Wá àwòrán nínú ojú-ìwé yìí - ààyè àwọn àwòrán nínú àwọn àwòrán nínú àwọn àwòrán.

Pop, rock, EDM, jazz, ambient, classical, lo-fi, hip-hop intrumentals gbogbo wọn ti ṣe afihan nípa ìṣàfarawé. Niche genres (gamelan, Carnatic, throat singing) jẹ́ ìdáràn - ṣàfihàn àwọn intrumentals nípa ìṣàfihàn fun àwọn ìrísí-lẹ́tà tí o dara jù lọ.

AudioLDM 2 n ṣiṣẹ́ lorí GPUs̀ wà ní pàtó lórí àwọn ayẹyẹ́ ọ̀fẹ́ rẹ̀ ní ọjọ́ akọkọ; $5 → 200,000 tokè tí a fi saǹ lórí. Tokè ~5,000 fun àkọsílẹ̀ kan.

WAV nípa ìpéwọ̀n (kò ní ìdáràn, tí ó tílẹ̀ fún ìṣàfarawé. MP3 ní àwọn fáìlì àwọn fáìlì àwọn ìṣàfilọ́lẹ̀.

No — AudioLDM 2 returns a mixed track. To separate into stems, run the output through /music/separate/ which uses Demucs to extract vocals, drums, bass, and other.

Ya — /batch/ gba àtòjọ àwọn ìṣàmúlò-ètò. Àwọn àkọ́lé nínú /account/?tab=history nínú àwọn ìṣàmúlò-ètò bí àwọn àwọn àtòjọ-ẹ̀yàn. Fún ìdáràn, ló API.

Yes — POST your prompt to /v1/music/generate/ with model="AudioLDM 2". /api/ has the full reference including lyrics, duration, and tempo parameters.

AudioLDM 2 does not reproduce copyrighted compositions — outputs are synthesized fresh. Free.ai grants commercial use; you keep the rights to your generated tracks. Naming an artist in the prompt asks for "in the style of" — the actual audio is original.

15 sekondi sí àwọn àkókò 2 nínú àkọ́lé kan nípa ìgbàyàn + inán. Àwọn àwọn ìṣàmúlò-ètò Premium tí wọ́n tí ìjádé. Lò bọ́tìnì ìjádé láti pa táàbù náà — àwọn àwọn ààtò àwọn ààtò nínú /àwọn à

Ya — a tí kò lè fi àwọn àkọ́lé ààtòjútó pamọ́. Fun àwọn àkọ́lé tí wọ́lù àwọn àwòrán àti àwọn àwòrán, kọ́ kọ́ọ̀kan@free.ai láti fi àwọn àkọ́lé pamọ́ sí ojú-ìwé àwọn

AudioLDM 2

Lò nípa API

Àwọn ìṣàmúlò-ètò ìsàlẹ̀-ètò

Àwọn Àtòjọ-ẹ̀yàn

Àwọn àwọn ààtò tí AudioLDM 2 lágbára

Ìgbà wo ní àkọlé AudioLDM 2 lè jẹ́?

Àwọn àwọn àwòrán

Àwọn ìṣàfarawé àwọn ìṣàfarawé wo ni AudioLDM 2 ń gbọ́?

Ìgbà wo ní AudioLDM 2 lò nínú àkọ́kọ́ kan?

Ìgúnrégé àwòrán wo ní AudioLDM 2 náà ń pàdé sí?

Can AudioLDM 2 generate stems (vocal + drums + bass separately)?

Can I batch generate with AudioLDM 2?

Àwọn ààyè-iṣẹ́ fún AudioLDM 2

Kini nipa àwọn ẹ̀yàn ìṣàfarawé àtí mò bá ṣàfihàn àwọn ààtòjọ-ẹ̀yàn AudioLDM 2?

Ìgbà wo ní AudioLDM 2 fẹ́ láti ṣàfihàn?

Ń lè gba ìṣàfarawé ìpamọ́ tí AudioLDM 2 bá ṣẹ̀dà?

Gba 10,000 Free Tokens

Wá - Gba 10K Free Tokens!

Tí o fẹ́ láti mú diẹ̀ sii?