Tag fantatry ny modely voafaritra — tsindrio mba hametrahana iray ao anatin'ny lahatsoratrao izay misy azy:
Mamakiana lahabolana tsotra io modely io, ka tsy raharahaina ny tag anatin'ny andalana. Raha mila fihetseham-po mifototra amin'ny tag ianao, dia miova ho modely maneho fihetseham-po toy ny Orpheus na Bark.
Fanomezana ny teny natoraly. Nanome voninahitra ny Qwen3-TTS androany; modely hafa hanehoana ny tena ho avy tsy ho ela.
Tsy mandray an-tànana ny toro-làlan'ny endriky ny teny ity modely ity — ampio ilay modely izay mandray an-tànana izany (ohatra: Qwen3-TTS).
Mamaritra ny fanononana safidy (teny = fanononana):
-12
+12
Manara-maso ny fanehoana (0 = tsy misy ifandraisany, 1 = tena fanehoana)
Ny lanjany amin'ny famaritana tsy misy mpizara (ny avo kokoa = manaraka ny toro-hevitra kokoa)
Mamaritra ny endriky ny feo amin'ny teny natoraly (ity no ampiasaina amin'ny Parler fa tsy ny feo efa voafaritra mialoha)
Lamin'ny takila Dia: Ampiasao ny tag [S1] sy [S2] mba hamantarana mpiteny samihafa. Ohatra: [S1] Misaotra! [S2] Misaotra, ahoana ny toe-draharaha?
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.
Tsara indrindra ho an'ny: 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.
Efa nahatratra ny fetra amin'ny modely maimaimpoana ianao. Ampitomboy ny isa mba hahazoana marika fanampiny, na mividy fonosana marika mba hampiasana modely premium.
