FreyaTTS

FreyaTTS TTS

A compact Turkish text-to-speech model that outputs 48 kHz audio without a phonemizer.

Sa palibot sa Aïn Ouaïd. Limitahan sa 5,000 ka karakter

Ang yuta palibot sa Ssm kay medyo kabukiran.

<speak><prosody rate="slow">Slow speech</prosody></speak>

Ang mga tag sa gipili nga modelo makasabut - i-klik aron ihulog ang usa sa imong teksto diin kini mahitabo:

Ang modelong kini mobasa sa yano nga teksto, busa ang mga inline tags gi-ignore. Alang sa mga tag-based nga emosyon, i-usab sa usa ka ekspresyonal nga modelo sama sa Orpheus o Bark.

Ang yuta palibot sa Cerro La Pronunciación kay lain-lain.

-12 +12
0.5x 2.0x
Sa rehiyon palibot sa Piper, mga lawis talagsaon komon.
Ang imong na-generate nga audio mopakita dinhi. Pilia ang usa ka modelo, i-type ang teksto, ug i-klik ang Genere.
Ang audio maayong natukod
0:00
I-download ang Audio Sa palibot sa Srt. Hapit nalukop sa kaumahan ang palibot sa 24H.
Sa palibot sa ‘En ‘Alam. Ang yuta palibot sa $5 Mine kay lain-lain.
Love TTS.ai? Tell your friends!

Sa palibot sa Aïn el Aïd. FreyaTTS

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.

Sa palibot sa Best.: Turkish narration, voice agents, and any Turkish audio that needs high sample-rate output

Lawak ang lahat FreyaTTS Tingog

Sa palibot sa Glance.

Pag-uswag
Freya
Lisensiya
Apache 2.0
Tigre
free
Katulin
fast
Sa palibot sa Klondike.
Wala
Linguistics
Turkish
Maksimum nga mga karakter
2000

FreyaTTS Tingog

Freya (Turkish)

Turkish
Sa palibot sa Standard. Female

FreyaTTS Sa palibot sa FAQ.

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.
← Sa palibot sa Votos.