Teks-ka-waca Agen Musik Audio dadi Teks Kloning swara Desain swara Marketplace Luwih
Report Bug / Feature Request

Tool

Sign Up Free
Kita Seller Your Voice

Bantuan mbangun TTS kanggo saben basa

Kita mung butuh2jam rekaman saben basa kanggo nglatih model TTS. Kontribusi swaramu kanggo mbantu nyiptakaké teks-ka-ucapan gratis, sumber terbuka kanggo kabeh 100 basa.

32 basa sing didhukung 68 basa butuh pitulungmu
1

Rekaman

Baca tembung-tembung ing basamu nganggo mikrofonmu. Saben rekaman butuh 5-15 detik.

2

We Train

Sawisé kita nglumpukaké2+ jam rekaman kualitas saben basa, kita nyetel model TTS ing data. Model diterbitaké kanthi sumber terbuka.

3

Saben wong

Model kang dilatih bisa ditemokaké ing TTS.ai kanthi gratis. Para kontributor bisa entuk 1 kredit kanggo saben rekaman kang diterima.

Progresi Basa

Afrikaans
0.0h / 20h 0 helpers
Albanian
0.0h / 20h 0 helpers
Amharic
0.0h / 20h 0 helpers
Armenian
0.0h / 20h 0 helpers
Assamese
0.0h / 20h 0 helpers
Azerbaijani
0.0h / 20h 0 helpers
Basque
0.0h / 20h 0 helpers
Belarusian
0.0h / 20h 0 helpers
Bengali
0.0h / 20h 0 helpers
Bosnian
0.0h / 20h 0 helpers
Bulgarian
0.0h / 20h 0 helpers
Burmese
0.0h / 20h 0 helpers
Catalan
0.0h / 20h 0 helpers
Chichewa
0.0h / 20h 0 helpers
Croatian
0.0h / 20h 0 helpers
Esperanto
0.0h / 20h 0 helpers
Estonian
0.0h / 20h 0 helpers
Filipino
0.0h / 20h 0 helpers
Galician
0.0h / 20h 0 helpers
Gujarati
0.0h / 20h 0 helpers
Haitian Creole
0.0h / 20h 0 helpers
Hausa
0.0h / 20h 0 helpers
Hebrew
0.0h / 20h 0 helpers
Igbo
0.0h / 20h 0 helpers
Indonesian
0.0h / 20h 0 helpers
Irish
0.0h / 20h 0 helpers
Javanese
0.0h / 20h 0 helpers
Kannada
0.0h / 20h 0 helpers
Khmer
0.0h / 20h 0 helpers
Kinyarwanda
0.0h / 20h 0 helpers
Kurdish
0.0h / 20h 0 helpers
Kyrgyz
0.0h / 20h 0 helpers
Lao
0.0h / 20h 0 helpers
Latvian
0.0h / 20h 0 helpers
Lithuanian
0.0h / 20h 0 helpers
Luxembourgish
0.0h / 20h 0 helpers
Macedonian
0.0h / 20h 0 helpers
Malagasy
0.0h / 20h 0 helpers
Malay
0.0h / 20h 0 helpers
Malayalam
0.0h / 20h 0 helpers
Maltese
0.0h / 20h 0 helpers
Maori
0.0h / 20h 0 helpers
Marathi
0.0h / 20h 0 helpers
Mongolian
0.0h / 20h 0 helpers
Odia
0.0h / 20h 0 helpers
Pashto
0.0h / 20h 0 helpers
Persian
0.0h / 20h 0 helpers
Punjabi
0.0h / 20h 0 helpers
Shona
0.0h / 20h 0 helpers
Sindhi
0.0h / 20h 0 helpers
Sinhala
0.0h / 20h 0 helpers
Slovenian
0.0h / 20h 0 helpers
Somali
0.0h / 20h 0 helpers
Sundanese
0.0h / 20h 0 helpers
Tajik
0.0h / 20h 0 helpers
Tamil
0.0h / 20h 0 helpers
Tatar
0.0h / 20h 0 helpers
Telugu
0.0h / 20h 0 helpers
Thai
0.0h / 20h 0 helpers
Turkmen
0.0h / 20h 0 helpers
Urdu
0.0h / 20h 0 helpers
Uyghur
0.0h / 20h 0 helpers
Uzbek
0.0h / 20h 0 helpers
Welsh
0.0h / 20h 0 helpers
Xhosa
0.0h / 20h 0 helpers
Yiddish
0.0h / 20h 0 helpers
Yoruba
0.0h / 20h 0 helpers
Zulu
0.0h / 20h 0 helpers
Arabic
TTS kasedhiya
Chinese
TTS kasedhiya
Czech
TTS kasedhiya
Danish
TTS kasedhiya
Dutch
TTS kasedhiya
English
TTS kasedhiya
Finnish
TTS kasedhiya
French
TTS kasedhiya
Georgian
TTS kasedhiya
German
TTS kasedhiya
Greek
TTS kasedhiya
Hindi
TTS kasedhiya
Hungarian
TTS kasedhiya
Icelandic
TTS kasedhiya
Italian
TTS kasedhiya
Japanese
TTS kasedhiya
Kazakh
TTS kasedhiya
Korean
TTS kasedhiya
Nepali
TTS kasedhiya
Norwegian
TTS kasedhiya
Polish
TTS kasedhiya
Portuguese
TTS kasedhiya
Romanian
TTS kasedhiya
Russian
TTS kasedhiya
Serbian
TTS kasedhiya
Slovak
TTS kasedhiya
Spanish
TTS kasedhiya
Swahili
TTS kasedhiya
Swedish
TTS kasedhiya
Turkish
TTS kasedhiya
Ukrainian
TTS kasedhiya
Vietnamese
TTS kasedhiya

Kontribusi Rekaman

Nyiptakaké akun gratis kanggo miwiti kontribusi swaramu. Rekamanmu mbantu nyiptakaké model TTS gratis kanggo saben wong.

Langganan kanggo Kontribusi

Sampeyan wis ngomong basa sing didhukung?

Sampeyan isih bisa mbantu kanthi nyawiji swara sampeyan kanggo wong liya kanggo digunakake. Unggah rekaman swara lan biarake komunitas kloning swara sampeyan kanggo proyek TTS.

Seller Your Voice

Pitakon kang Kadhangkala Ditakoni

Program kontribusi swara ngidini sampeyan nyumbang rekaman swara cekak kanggo mbantu mbangun model TTS gratis, sumber terbuka kanggo basa sing saiki ora didhukung. Rekaman sampeyan mbantu nglatih model AI sing bisa digunakake sapa wae.

Pilih basamu, banjur baca tembung-tembung nganggo mikrofonmu. Saben rekaman dawané 5-15 detik. Sampeyan bisa nyedhiyani sapérangan utawa sapérangan rekaman kaya sing dikarepake. Sedaya rekaman sing ditarima bakal digunakaké kanggo nglatih model TTS gratis kanggo basamu.

Rekaman-rekaman kang ditarima mung digunakaké kanggo nglatih modél TTS sumber-bukah. Modél-modél kang dilatih dirilis ing ngisor lisensi Apache 2.0 ing GitHub lan HuggingFace. Rekaman-rekamanmu ora didol utawa dibagi karo pihak katelu. Para kontributor dikreditaké ing rilis modél.

Kita saiki nyengkuyung 32 basa kanthi model TTS. 68 basa kang isih ana ing situs kita butuh data swara komunitas. Halaman kontribusi nuduhaké bar kemajuan kanggo saben basa — basa kang cedhak karo jam targeté diprioritasikaké kanggo latihan.

Kita target 20 jam rekaman saben basa kanggo model siji-pengucap sing apik. Kanthi 100+ kontributor saben rekaman 10-15 menit, kita bisa tekan tujuan iki. Malah kontribusi cilik mbantu — saben rekaman ndadèkaké kita luwih cedhak.

Ya! Para kontributor nampa kredit TTS kanggé rekaman ingkang dipuntampi. Para kontributor ingkang paling inggil pikantuk badge "Voice Pioneer" lan dipunkreditaken kanggé model ingkang dipunlatih. Paduka ugi pikantuk akses awal kanggé model TTS basa kawula sadurungé dipunrilis kanggé umum.

Ya! Data kang luwih akèh nambahi kualitas. Kontribusi kanggo basa-basa sing didhukung mbantu kita mbangun model multi-speaker kanthi variasi swara sing luwih akèh, aksen sing luwih apik, lan alamiah sing luwih apik.

Ruangan sing surem lan mikrofon apa wae — malah telpon utawa laptop bisa digunakake. Kanggo kualitas paling apik, gunakake headset utawa mikrofon USB. Hindari swara latar mburi, gema, lan pirang-pirang speaker. Sistem bakal mriksa kualitas audio sadurunge nampa.

Saben rekaman ngliwati verifikasi kualitas otomatis: rasio sinyal-ka-noise (SNR > 20dB), transkripsi Whisper sing cocog karo ukara sing diarepake, durasi ing njero jembaré target, lan deteksi speaker tunggal. Rekaman sing gagal bisa direkam maneh.

Sampeyan bisa ngadhepi antarmuka kontribusi tanpa akun, nanging rekaman disambungake karo akun TTS.ai supaya kita bisa menehi kredit kanthi bener lan nglacak kontribusi sampeyan. Pendhaftaran gratis lan butuh 30 detik.

Sawisé basa kang cukup akèh datané (biasané 20+ jam), tim kita miwiti latihan model. Latihan iki mbutuhaké 1-2 minggu ing GPU cluster kita. Model kang dihasilaké dites, diterbitaké ing HuggingFace ing Apache 2.0, lan ditambahaké ing TTS.ai kanggo sapa wae bisa nggunakake.

Ya. Dashboard kontribusi nuduhaké bar kemajuan kanggo saben basa, kalebu total rekaman, jam sing dikumpulake, jumlah kontributor, lan persentase kanggo target pelatihan. Sampeyan uga bisa ndeleng statistik kontribusi pribadi sampeyan.
5.0/5 (1)

What could we improve? Your feedback helps us fix issues.

Siap kanggo miwiti?

Nggabungake gratis lan njaluk 15,000 karakter. Ora perlu kertu kredit.

Sign Up Free View Pricing