StyleTTS 2

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

StyleTTS 2 ni an Àwọn àkọlé àwọn àkọlé tí Yinghao Aaron Li kọ̀. Ó ní ìmọ́ nínú Voice cloning without training data; expressive multilingual speech.. Ààyè àìṣàfilọ́lẹ̀ fún ara rẹ̀ ní àwọn GPUs Free.ai — láàyè láti pàtó àwọn ààyè àìṣàfilọ́lẹ̀ rẹ̀ ní ọjọ́ (500 ààyè fún kọ́ọ̀kan àwọn ìṣàmúlò-ètò). Ti fi silẹ labẹ MIT — 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/tts/ \
  -H "Authorization: Bearer sk-free-..." \
  -H "Content-Type: application/json" \
  -d '{"model":"styletts2","text":"hello world"}'

Àwọn Àkọsílẹ̀ Gba àwọn àwọn àmì-ìwé API

Àwọn ìṣàmúlò-ètò ìsàlẹ̀-ètò

Bark TTS

Cartesia Sonic 3 (real-time)

ElevenLabs Multilingual v2

ElevenLabs Turbo v2.5

Inworld TTS

Orpheus TTS

Parler TTS Large

PlayAI v3 TTS

Wá gbogbo àwọn ìṣàmúlò-ètò →

Àwọn Àtòjọ-ẹ̀yàn

StyleTTS 2 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.

Àwọn ìrànwọ́ SSML tí a fi yatọ̀ sí inú inú. Àwọn àmì-ìwé ìpàsẹ̀, àwọn àmì-ìwé àti àwọn àmì-ìwé ìṣàfarawé ní pàtó ní àwọn inú inú àwọn à

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.

StyleTTS 2 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 "StyleTTS 2" (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.

Ya — Free.ai n gba lórí ìlòòdù àwọn àwòrán tí a tì ṣẹ̀dà. Àwọn àwọn ìṣẹ̀dà ìṣàmúlò-ètò inú (Apache 2.0, MIT, tàbí àwọn àwọn ìpéwọ̀n tí a fi pamọ́) tí a fi hàn ní ààyè àwọn ààyè àwọn ìṣàmúlò-ètò; nínú ìṣàmúlò-ètò yìí tumọ̀ sí àwọn àwòrán, àwọn àwọn àkọsílẹ̀, àwọn àwọn ìṣàmúlò-ètò, àti àwọn ìṣàmúlò-ètò nínú àwọn ààyè.

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

StyleTTS 2

Lò nípa API

Àwọn ìṣàmúlò-ètò ìsàlẹ̀-ètò

Àwọn Àtòjọ-ẹ̀yàn

Àwọn ìtàn wo ni StyleTTS 2 ǹfà?

Does StyleTTS 2 have a recognizable accent?

Ń lè lo SSML láti StyleTTS 2?

Does StyleTTS 2 support streaming?

Ìgbà wo ní StyleTTS 2 lò nínú àwọn àkókò kan?

Ìgbà wo ní ìgbà jú àkọlé lọ fún StyleTTS 2?

Ń lè ráǹwá StyleTTS 2 nínú àwọn àwọn àwọn ààtò?

Àwọn ààyè-iṣẹ́ fún StyleTTS 2

Do I need consent to clone a voice with StyleTTS 2?

Ńpà wò nípa àìdárà àti StyleTTS 2?

Àwọn àtòjọ-ẹ̀yàn StyleTTS 2 ní ìdáràn fún ìlò àwọn iṣẹ́ ọ̀fẹ́?

Ń lè gba ìṣàfarawé ìpamọ́ tí StyleTTS 2 bá ṣẹ̀dà?

Gba 10,000 Free Tokens

Wá - Gba 10K Free Tokens!

Tí o fẹ́ láti mú diẹ̀ sii?