Persian

Àwọn ìṣàmúlò-ètò fa Neutral

MOSS-TTS

Persian ní ìrànwọ́ AI neutral tí a fi ìpapọ̀ láti inú ìṣàmúlò-ètò àkọlé-si-ìbàlẹ̀ MOSS-TTS. Àwòrán yìí tí a fi premium-level kọ́ ní fa àti tí o fi ìṣàmúlò-ètò ìṣàfihàn tí a ní ìṣàfihàn Ìkọ́kọ́-quality pamọ́. Ààyè tí a fi ṣẹ́dá ààyè yìí nípa ìṣàfarawé àwọn ààyè tí a fi ṣẹ́dá fún àwọn ìṣàmúlò-ètò atí ìṣàmúlò-ètò ìṣàfarawé tí a fi ṣẹ́dá fún 5/5, Persian jẹ́ ìṣàmúlò-ètò tí o dara fún audiobooks, long-form content, multilingual production. Ìjánu-ìṣàfilọ́lẹ̀ {móòdù} ní a tí kọ́ nípa {àwọn ìṣàfilọ́lẹ̀} under the Apache 2.0 license, tí o fi jẹ́ àìdára fun ìlò àìṣe. Àwọn ìṣẹ̀dá ìwọ̀n ni: ultra-long generation, 20 languages, voice cloning, duration control, pronunciation control. Módélù {módè́lì} náà tun ń gbọ́ ìṣàmúlò-ètò ìṣàfarawé àwọn ìṣàmúlò-ètò àwọn ìṣàmúlò-ètò tí a fi pamọ́ sípapọ̀.

Àwọn ìṣàmúlò-ètò

Wá Àwòrán Yìí Gbogbo wọn MOSS-TTS Àwọn Àmì-ìwé

Àwọn Àlàyé Àwọn Àwọn Àwọn Àwọn

Àwọn ìṣàmúlò-ètò	MOSS-TTS
Àwọn Àkọlé	OpenMOSS
Àwọn ìkúndùǹ
Ìjánu-ìṣàmúlò-ètò	Àwọn àwọn àwọn àwọn
Àwọn Ààyè-iṣẹ́	Apache 2.0
Àwọn Àwọn Àkọlé	Tí a Fẹ̀
Àwọn àwọn ààyè-iṣẹ́	Àwọn àyọkà ìṣàfarawé
Àwọn Àtòjọ-ẹ̀yàn	8B
Àwọn Ìṣàmúlò-ètò	Delay Transformer
Àtòjọ-ẹ̀yàn Ìṣàmúlò-ètò	500000 àwọn àgójọpọ̀
_Táàbù	2026

Àwọn Ìṣàmúlò-ètò Tí O darà fún Persian

Àwọn ìṣàmúlò-ètò tí a fi pamọ́ fún àwọn àbùdá ìrànwọ́ àwòrán yìí

Àwọn àkọlé àwọn àkọlé

Lo Persian láti sọ àwọn ìròyìn ìṣàfarawé àwọn ìṣàmúlò-ètò ìpẹ̀lú àwọn ìṣàfihàn àti àwọn ìṣàfihàn àwọn ìṣàfihàn.

Àwọn Àmì-ìwé Àwòrán

Fi àwọn àkọlé àwọn àkọlé àwọn àwòrán YouTube, àwọn àwọn ààyè-iṣẹ́, àti àwọn àwọn ààyè-iṣẹ́ media ìmọ̀yàn.

Àwọn Pódíẹ̀tì & Àwọn Àkọ́kọ́

Àwọn ìṣàfilọ́lẹ̀ ìṣàfilọ́lẹ̀ ìṣàfilọ́lẹ̀ ìṣàfilọ́lẹ̀ ìṣàfilọ́lẹ̀ ìṣàfilọ́lẹ̀ ìṣàfilọ́lẹ̀ ìṣàfilọ́lẹ̀

Àwọn àwọn àmì-ìwé àwọn ìṣàmúlò-ètò

Klọ́ǹọ̀ ìṣàfarawé àwọn ìrísí-lẹ́tà yìí láti ṣẹ̀dà ìrísí-lẹ́tà TTS tí a fi àwọn àmì-ìwé kọ́ọ̀kan pamọ́.

Díẹ̀ MOSS-TTS Àwọn Àmì-ìwé

Àwọn ìrànwọ́ mìíràn láti inú àwọn ìṣàmúlò-ètò TTS

Arabic

Arabic Neutral

Chinese

Chinese Neutral

Czech

Czech Neutral

Danish

Danish Neutral

Default

English Neutral

French

French (France) Neutral

Wo gbogbo wọn MOSS-TTS Àwọn Àmì-ìwé

Àwọn Àtòjọ-ẹ̀yàn

MOSS-TTS from OpenMOSS supports generation of up to 1 hour of continuous speech across 20 languages. Features token-level duration control, phoneme-level pronunciation control via IPA/Pinyin, and code-switching between languages. The 8B production model delivers state-of-the-art quality with zero-shot voice cloning from reference audio.

MOSS-TTS was developed by OpenMOSS and is released under the Apache 2.0 license, which permits commercial use of generated audio.

MOSS-TTS supports 19 languages: English, Chinese, German, Spanish, French, Japanese, Italian, Hungarian and more.

MOSS-TTS is in the Premium tier — 4 credits per 1,000 characters. You can preview any MOSS-TTS voice for free before generating full audio.

MOSS-TTS has moderate generation speed. Generation typically takes a few seconds depending on text length.

MOSS-TTS is rated 5/5 for audio quality on TTS.ai. It delivers studio-grade, human-like speech.

Yes, MOSS-TTS supports zero-shot voice cloning. Upload 5-30 seconds of reference audio to create a custom voice.

Yes, MOSS-TTS is specifically recommended for audiobooks, long-form content, multilingual production. Its ultra-long generation, 20 languages, voice cloning capabilities make it an excellent choice for this use case.

Yes, MOSS-TTS is licensed under Apache 2.0, which allows commercial use. Audio generated with MOSS-TTS voices can be used in videos, podcasts, apps, games, and any other commercial project.

Ya, gbogbo àwọn ìrànwọ́ ní pàtó TTS.ai ló ń ló àwọn àwọn àwòrán-ìṣàfilọ́lẹ̀ àìfilọ́lẹ̀-ìṣàfilọ́lẹ̀ (MIT, Apache 2.0). Àwòrán tí a ṣẹ̀dà nípa rẹ̀ láti lò nínú àwọn àwòrán, àwọn ìṣàfilọ́lẹ̀, àwọn ere, àwọn ìṣàfilọ́lẹ̀ àwọn iṣẹ́ iṣẹ́.

Send a POST request to /api/v1/tts/ with the model name and voice ID. See our API Documentation page for code examples in Python, JavaScript, Go, and cURL.

Yà, tẹ bọ́tìnì ìṣàmúlò-ètò náà nínú ojú-ìwé yìí láti gbọ́ àwọn ààyè-iṣẹ́. O lè kọ́ àwọn àkọlé àwọn ìṣàmúlò-ètò rẹ̀ nínú ojú-ìwé Àkọlé-si-Ìṣàfihàn àti láti ṣẹ̀dá àwọn ìṣàfihàn àìfẹ́ nínú àwọn ìròyìn wòye.

Àwọn ìṣàfarawé Persian Àwọn ààyè-iṣẹ́

Ṣàfihàn àwọn àyọkà àti ìgbọ̀n àwòrán láti inú Persian. Free to use.

Ṣẹ̀dà Àwọn Àkọlé Ṣàfihàn

Persian

Àwọn Àlàyé Àwọn Àwọn Àwọn Àwọn

Àwọn Ìṣàmúlò-ètò Tí O darà fún Persian

Àwọn àkọlé àwọn àkọlé

Àwọn Àmì-ìwé Àwòrán

Àwọn Pódíẹ̀tì & Àwọn Àkọ́kọ́

Àwọn àwọn àmì-ìwé àwọn ìṣàmúlò-ètò

Díẹ̀ MOSS-TTS Àwọn Àmì-ìwé

Arabic

Chinese

Czech

Danish

Default

French

Àwọn Àtòjọ-ẹ̀yàn

What is MOSS-TTS TTS?

Who developed MOSS-TTS?

What languages does MOSS-TTS support?

How much does it cost to use MOSS-TTS voices?

How fast is MOSS-TTS at generating speech?

What is the audio quality of MOSS-TTS?

Can I clone a voice with MOSS-TTS?

Is MOSS-TTS suitable for audiobooks?

Can I use MOSS-TTS voices commercially?

Ń lè lò ìrànwọ́ yìí fún àwọn ìṣàmúlò-ètò ọ̀fẹ́?

Bawo ni mo ṣe le lo àwòrán yìí láti inú API?

Ń lè wòye àwòrán àwòrán láti inú àwòrán?

Àwọn ìṣàfarawé Persian Àwọn ààyè-iṣẹ́