Clibeanna a thuigeann an tsamhail roghnaithe — cliceáil chun ceann a scaoileadh isteach i do théacs nuair a tharlaíonn sé:
Léann an tsamhail seo gnáth- théacs, mar sin déantar neamhaird ar chlibeanna inlíne. Chun mothúchán clibbhunaithe a chruthú, athraigh go samhail léiritheach cosúil le Orpheus nó Bark.
Cues seachadta teanga nádúrtha. Onóracha ag Qwen3-TTS inniu; samhlacha sainráiteacha eile ag teacht go luath.
Ní thacaíonn an tsamhail seo le treoracha stíle — athraigh go samhail a dhéanann (m.sh. Qwen3-TTS).
Rialú ar an sainráiteacht (0 = neodrach, 1 = an- sainráiteach)
Meáchan treorach saor ó aicmitheoir (níos airde = níos mó leanúnach)
Déan cur síos ar an stíl gutha i dteanga nádúrtha (úsáideann Parlaimint é seo in ionad guthanna réamhshocraithe)
Formáid Dialóg Dia: Úsáid clibeanna < code > [S1] agus < code > [S2] chun cainteoirí éagsúla a mharcáil. Sampla: < code > [S1] Dia duit! [S2] Dia duit, cad atá ar siúl agat?
Is samhail gutha préimhe é seo, atá ar fáil ar aon phlean íoctha. Is féidir leat réamhamharc a dhéanamh ar a guthanna saor in aisce leis an gcnaipe seinn in aice leis an roghnóir gutha.
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.
Is Fearr le haghaidh: 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.
Cuir isteach do r-phost chun labhairt a ghiniúint saor in aisce, nó cláraigh le haghaidh 15,000 carachtar bónais.
Níl aon phasfhocal ag teastáil — cuirfimid nasc chugat ar ríomhphost chun ceann a shocrú níos déanaí.
Teorainn Sraithe Saor Bainte Amach
Tá tú ag úsáid do 5,000 carachtair laethúil saor in aisce.Cruthaigh cuntas saor in aisce a fháil 15,000 carachtair bónas móide 10,000 carachtair saor in aisce gach mí.
