Tags ang napili modelo nauunawaan — i-click upang ihulog ang isa sa iyong teksto kung saan ito ay nangyayari:
Ang modelong ito ay nagbabasa ng karaniwang teksto, kaya inline tags ay hindi pinapansin. Para sa tag-based na damdamin, lumipat sa isang makahulugang modelo tulad ng Orpheus o Bark.
Natural-language delivery cues. Pinarangalan ng Qwen3-TTS ngayon; iba pang mga masining na modelo darating sa lalong madaling panahon.
Ang modelong ito ay hindi sumusuporta sa mga tagubilin ng estilo — lumipat sa isang modelo na ginagawa (halimbawa Qwen3-TTS).
Tukuyin ang mga pasadyang mga panlapi (word = panlapi):
-12
+12
Controls katangian ng pagpapakita (0 = neutral, 1 = napaka-katangian ng pagpapakita)
Classifier-free gabay timbang (mas mataas = mas prompt-sunod)
Ipaliwanag ang estilo ng boses sa natural na wika (Parler gumagamit ito sa halip ng preset na boses)
Dia Dialog Format: Ang mga salitang ito ay maaaring isulat sa mga titik na [S1] at [S2]. Halimbawa: [S1] Hello there! [S2] Hi, how are you?
Ito ay isang premium na modelo ng boses, magagamit sa anumang bayad na plano. Maaari pa ring mag-preview ng mga boses nito nang libre sa play button sa tabi ng boses picker.
FreyaTTS-small is a 183-million-parameter model built for one language and built well. It is a non-autoregressive conditional flow-matching diffusion transformer that reads Turkish directly at the character level — 92 symbols, no phonemizer and no grapheme-to-phoneme stage, which removes a whole class of mispronunciation that pronunciation dictionaries introduce. It generates in a frozen AudioVAE2 latent space and decodes to 48 kHz mono, more than double the sample rate of the piper Turkish voice, so the output carries treble detail that a 22 kHz model simply cannot represent. On the Freya-TR-Eval benchmark it reaches 8.0% word error rate, placing it ahead of both XTTS-v2 and F5-TTS among open sub-billion-parameter Turkish systems, and it runs fast enough for real-time use at roughly a tenth of real time.
Pinakamahusay para sa: Turkish narration, voice agents, and any Turkish audio that needs high sample-rate output
It was trained from scratch on Turkish speech alone rather than adapted from a multilingual model. Specialising lets a 183M-parameter model compete with far larger multilingual systems on Turkish, but it means the model has no ability to read other languages — requests in another language are rejected rather than mispronounced.
Most open TTS models emit 22.05 kHz or 24 kHz, which caps reproducible audio at around 11-12 kHz and audibly dulls sibilants. FreyaTTS decodes to 48 kHz, the standard sample rate for video and broadcast, so its output drops into a production timeline without upsampling.
No. FreyaTTS has a single fixed speaker and does not support cloning. For a cloned Turkish voice use one of our zero-shot cloning models instead.
Many TTS systems first convert text into phonemes using a pronunciation dictionary, and anything missing from that dictionary — new words, names, loanwords — gets guessed. FreyaTTS reads the characters themselves, so Turkish spelling, which is highly regular, maps to sound without that lossy middle step.
Ipasok ang iyong email upang makakuha ng 15,000 libreng mga character at panatilihin ang pagbuo ng pagsasalita.
Walang kailangang password — ipapa-email sa iyo ang isang link upang magtakda ng isa mamaya.
Libreng Limita sa Antas Naabot
Ginamit mo na ang iyong 5,000 libreng araw-araw na mga character. Lumikha ng isang libreng account upang makakuha ng 15,000 bonus na mga character pati na rin ang 10,000 libreng mga character bawat buwan.
Naabot mo na ang iyong libreng limitasyon ng modelo. Mag-upgrade para sa higit pang mga character, o bumili ng isang character pack upang gamitin ang mga premium na modelo.
