VibeVoice

Free.ai (self-hosted) · tts · ~500 tokens per clip · 4.3 Lọ́wọ́lọ́wọ́ 3 Àwọn òǹlò tí a fi pamọ́

Àkọlé àti àwọn àmì-ìwé

Àwọn àmì-ìwé

Ìjánu-ìṣàmúlò-ètò

~500 tokens per clip

VibeVoice ni an Àwọn àkọlé àwọn àkọlé tí Microsoft kọ̀. Ó ní ìmọ́ nínú Long-form audiobooks and multi-speaker podcasts with up to four distinct voices.. Self-hosted on Free.ai GPUs — runs free against your daily token pool (500 tokens fún kọ́ọ̀kan àwọn ìṣàmúlò-ètò). Ti fi silẹ labẹ MIT — lilo iṣowo ti gba laaye lori Free.ai.

Lò nípa API

curl -X POST https://api.free.ai/v1/tts/ \
  -H "Authorization: Bearer sk-free-..." \
  -H "Content-Type: application/json" \
  -d '{"model":"vibevoice","text":"hello world"}'

Àwọn Àkọsílẹ̀ Gba àwọn àwọn àmì-ìwé API

Àwọn Àtòjọ-ẹ̀yàn

VibeVoice ǹfàyè gba àwọn ìtàn tí a tí fi pamọ́. Àtòjọ tí a fi pamọ́ nípa ìpéwọ̀n náà; àwọn àkọlé nípa ojú-ìwé yìí gba àwọn àkọlé tí a fi pamọ́. Wòyè /wòyè/ fún àwọn àwọn ìtàn tí a fi pamọ́ tí o bà fẹ́ ìtàn kan.

Àwọn iǹinà ìṣàmúlò-ètò ìṣàmúlò-ètò àwọn iǹinà ìṣàmúlò-ètò tí a fi pamọ́ fún Àwọn Inu-Ẹ̀yàn-Ameríkà nípa ìpéwọ̀n àti àwọn àwọn ìṣàmúlò-ètò tí a fi pamọ́ fún àwọn ìṣàmúlò-ètò tí kò jẹ́ Inu-Ẹ̀yàn-Ẹ̀yàn.

SSML support varies by engine. Pause, prosody, and emphasis tags are honored on most premium engines and on a few self-hosted ones. Plain text always works — no markup required.

Streaming TTS is available on premium engines via the /v1/tts/ API endpoint with stream=true. The web UI on this page returns the full clip once rendering finishes.

VibeVoice n ṣiṣẹ́ lorí GPUs wà. Ìgbà tí a bá fi pamọ́ lọ́wọ́lọ́wọ́ lọ́wọ́lọ́wọ́. Tí a bá fi pamọ́ lọ́wọ́lọ́wọ́, àwọn tókènì tí a pàyàn bá bẹrẹ ní $5 → tókènì 200,000. Nígbà kan, tókènì ~5 fún àwọn àbùdá kan, àwọn tókènì kékeré jú 100 fún àwọn kọ́lọ́wọ́.

Lẹ́ẹ̀kaǹ àwọn àmì-àṣírí 5,000 nínú ibeere kan nínú UI wẹ́ẹ̀bù. Fun àwọn àwọn ààyè tí o jú lọ (àkọ́lé àwọn àkọ́lé, àwọn àkọ́lé tí o tí ìgbà, lo /àwòrán/àkọ́òlù/ tí ò fi àwọn àwọn ààyè kọ́ọ̀kaǹ pamọ́, tàbí pé API nínú lìlọ́ọ̀kan.

Ya — POST àtòjọ àwọn àyọkà sí /v1/tts/batch/, tàbí lo ààyè-iṣẹ́ UI ni /àyè-iṣẹ́/ láti ṣí TTS sí àwọn ìjánu-ìjánú pípẹ (gẹ́gẹ́ bíi, fàyè gbàyé → sọ̀rọ̀ → kọ́ọ̀kan).

Yà — Àkọ́lé PỌ́S̀T̀ sí /v1/tts/ láti àwòrán "VibeVoice" (tabí àwọn àgbèwọlé nípa ojú-ìwé yìí). Wáẁẹ̀ tàbí MP3. Wòye /api/ fún àwọn àgbèwọlé àti àwọn àgbèwọlé SDK.

Ojú-ìwé yìí ní àkọlé-si-ìbàlẹ̀, kò ní ìṣàfarawé àwọn àmì-ìwé — àwọn àmì-ìwé ní ìpéwọ̀n inán. Fún ìṣàfàwé àwọn àmì-ìwé (ìṣàfihàn àwòrán ìṣàfihàn), wòyè /voice/clone/, tí ò bá fẹ́ pé ò ní àwọn ìṣẹ̀dà àwọn àmì-ìwé àti àwọn ìṣẹ̀dà àwọn àmì-ìwé.

Àwọn inẹ̀nì tí a fi pamọ́ fún ara wa tí n ṣiṣẹ́ lori GPUs Free.ai-tí a fi pamọ́; kò si ohunkohun tí n pá àwọn sáà wa. Inẹ̀nì Premium ń lọ́wọ́ àkọ́lé sí àwọn onímọ̀ ìṣàfilọ́lẹ̀ àwọn módè̀lì tí a fi pamọ́ sípàlẹ̀. A kò kọ́ àwọn àgbéwọlé rẹ̀ láti fi data pamọ́.

Yes — Free.ai grants commercial use of generated audio. The engine's underlying license (Apache 2.0, MIT, or vendor terms) is shown above and on the model reference page; in practice this means voiceovers, ads, podcasts, and apps are all in-scope.

Ya — àwọn iṣẹ́ tí kò bá jẹ́ ìṣàfarawé àwọn iṣẹ́ láti inú rẹ̀ sí àwọn ìṣàfilọ́lẹ̀ (àwọn àwọn àwọn tókè tí a fi pamọ́). Tó kò bá jẹ́ ìṣàfàyé àwọn iṣẹ́ ní ọjọ́ kejì, kọ̀ọ̀kan sì contact@free.ai.

VibeVoice

Àwọn Àtòjọ-ẹ̀yàn

Àwọn ìtàn wo ni VibeVoice ǹfà?

Does VibeVoice have a recognizable accent?

Ń lè lo SSML láti VibeVoice?

Does VibeVoice support streaming?

Ìgbà wo ní VibeVoice lò nínú àwọn àkókò kan?

Ìgbà wo ní ìgbà jú àkọlé lọ fún VibeVoice?

Can I run VibeVoice in batch?

Is there an API for VibeVoice?

Do I need consent to clone a voice with VibeVoice?

What about privacy with VibeVoice?

Àwọn àtòjọ-ẹ̀yàn VibeVoice ní ìdáràn fún ìlò àwọn iṣẹ́ ọ̀fẹ́?

Can I get a refund if VibeVoice fails?

Gba 10,000 Free Tokens

Wá - Gba 10K Free Tokens!

Tí o fẹ́ láti mú diẹ̀ sii?