Etiquetas que o modelo escollido entende - prema para deixar unha no texto onde ocorre:
Este modelo le texto simple, polo que se ignoran as etiquetas inline. Para emocións baseadas en etiquetas, cambie a un modelo expresivo como Orpheus ou Bark.
Indicacións de entrega de linguaxe natural. Honrado por Qwen3- TTS hoxe; outros modelos expresivos en breve.
Este modelo non admite instrucións de estilo; cambie a un modelo que o faga (por ex. Qwen3- TTS).
Controla a expresividade (0 = neutro, 1 = moi expresivo)
Peso de guía libre de clasificadores (maior = máis seguimento)
Describa o estilo de voz en linguaxe natural (Parler usa isto no canto das voces predefinidas)
Formato do diálogo Dia: Empregue as etiquetas < code> [S1] e < code> [S2] para marcar diferentes oradores. Exemplo: < code> [S1] Ola! [S2] Ola, como está?
Este é un modelo de voz premium, dispoñíbel en calquera plan de pago. Pode previsualizar as súas voces gratuitamente co botón de reprodución xunto ao selector de voz.
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.
Mellor para: 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.
Introduza o seu correo electrónico para seguir xerando fala de balde, ou subscríbase para obter 15. 000 caracteres extra.
Non se precisa contrasinal — enviarémoslle unha ligazón para configurar un máis tarde.
Acadouse o límite de niveis libres
Esgotou os seus 5. 000 caracteres diarios gratuítos. Cree unha conta gratuíta para obter 15. 000 caracteres extra máis 10. 000 caracteres gratuítos cada mes.
