Default Speaker

Àwọn ìpéwọ̀n English Neutral

MOSS-TTSD

Default Speaker ní ìrànwọ́ AI neutral tí a fi ìpapọ̀ láti inú ìṣàmúlò-ètò àkọlé-si-ìbàlẹ̀ MOSS-TTSD. Àwòrán yìí tí a fi standard-level kọ́ ní English 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, Default Speaker jẹ́ ìṣàmúlò-ètò tí o dara fún podcasts, audiobooks, dubbed dialogue, conversational content with multiple voices. 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: multi-speaker dialogue, up to 5 speakers, 60min coherent audio, voice cloning, 20 languages. 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-TTSD Àwọn Àmì-ìwé

Àwọn Àlàyé Àwọn Àwọn Àwọn Àwọn

Àwọn ìṣàmúlò-ètò	MOSS-TTSD
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 ìpéwọ̀n (2 àwọn ìṣàmúlò-ètò/1K àwọn àyọkà)
Àwọn Àtòjọ-ẹ̀yàn	7B
Àwọn Ìṣàmúlò-ètò	MOSS-TTS-Delay + dialogue continuation head
_Táàbù	2026

Àwọn Ìṣàmúlò-ètò Tí O darà fún Default Speaker

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

Àwọn àkọlé àwọn àkọlé

Lo Default Speaker 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-TTSD Àwọn Àmì-ìwé

Àwọn ìrànwọ́ mìíràn láti inú àwọn ìṣàmúlò-ètò TTS

Default (Chinese)

Chinese Neutral

Wo gbogbo wọn MOSS-TTSD Àwọn Àmì-ìwé

Àwọn Àtòjọ-ẹ̀yàn

MOSS-TTSD v1.0 from OpenMOSS is a 7B dialogue text-to-speech model that continues conversations from a short audio prompt. Supports up to 5 simultaneous speakers via [S1]/[S2] tags, zero-shot voice cloning from 3-10s reference audio, and up to 60 minutes of coherent multi-turn dialogue across 20 languages. Distinct from MOSS-TTS — TTSD is specialized for podcast/audiobook/dubbing workflows.

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

MOSS-TTSD supports 20 languages: English, Chinese, German, Spanish, French, Japanese, Italian, Korean and more.

MOSS-TTSD is in the Standard tier — 2 credits per 1,000 characters. You can preview any MOSS-TTSD voice for free before generating full audio.

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

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

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

Yes, MOSS-TTSD is specifically recommended for podcasts, audiobooks, dubbed dialogue, conversational content with multiple voices. Its multi-speaker dialogue, up to 5 speakers, 60min coherent audio capabilities make it an excellent choice for this use case.

Yes, MOSS-TTSD is licensed under Apache 2.0, which allows commercial use. Audio generated with MOSS-TTSD 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 Default Speaker Àwọn ààyè-iṣẹ́

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

Ṣẹ̀dà Àwọn Àkọlé Ṣàfihàn

Default Speaker

Àwọn Àlàyé Àwọn Àwọn Àwọn Àwọn

Àwọn Ìṣàmúlò-ètò Tí O darà fún Default Speaker

Àwọn àkọlé àwọn àkọlé

Àwọn Àmì-ìwé Àwòrán

Àwọn Pódíẹ̀tì & Àwọn Àkọ́kọ́

Àwọn àwọn àmì-ìwé àwọn ìṣàmúlò-ètò

Díẹ̀ MOSS-TTSD Àwọn Àmì-ìwé

Default (Chinese)

Àwọn Àtòjọ-ẹ̀yàn

What is MOSS-TTSD TTS?

Who developed MOSS-TTSD?

What languages does MOSS-TTSD support?

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

How fast is MOSS-TTSD at generating speech?

What is the audio quality of MOSS-TTSD?

Can I clone a voice with MOSS-TTSD?

Is MOSS-TTSD suitable for podcasts?

Can I use MOSS-TTSD 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 Default Speaker Àwọn ààyè-iṣẹ́