Oznake koje odabrani model razumije — kliknite da biste ih ubacili u tekst gdje se pojavljuju:
Ovaj model čita običan tekst, tako da se inline oznake ignoriraju. Za emocije zasnovane na oznakama, prebacite se na ekspresivni model poput Orpheusa ili Bark-a.
Prirodni jezik dostave signala. Poštovan od strane Qwen3-TTS danas; drugi ekspresivni modeli dolaze uskoro.
Ovaj model ne podržava stilske instrukcije - prebacite se na model koji ih podržava (npr. Qwen3-TTS).
Definirajte vlastite izgovore (riječ = izgovor):
-12
+12
Kontrolira ekspresivnost (0 = neutralno, 1 = vrlo ekspresivno)
Težina vodilja bez klasifikatora (više = više praćenja prompta)
Opis stila glasa u prirodnom jeziku (Parler koristi ovo umjesto unaprijed postavljenih glasova)
Dia Dialog Format: Koristite [S1] i [S2] oznake za označavanje različitih govornika. Primjer: [S1] Zdravo! [S2] Zdravo, kako ste?
Ovo je premium model glasa, dostupan na bilo kojem plaćenom planu. Još uvijek možete besplatno pregledati njegove glasove pomoću gumba za reprodukciju pored birača glasa.
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.
Najbolje za: 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.
Unesite svoj email da biste dobili 15.000 besplatnih znakova i nastavili sa stvaranjem govora.
Nema potrebe za šifrom — poslat ćemo vam link da ga postavite kasnije.
Dosegnuto ograničenje slobodnih nivoa
Iskoristili ste svojih 5000 besplatnih znakova dnevno.Napravite besplatni račun da biste dobili 15000 bonus znakova plus 10 besplatnih znakova svaki mjesec.
