Parler-TTS Large
Free.ai (self-hosted)
·
tts
·
~500 tokens per clip
·
4.3
kubva 3 1 mushandisi munyaya ino
Parler-TTS Large is a Kutaura-ku-tekisi built by HuggingFace. Strongest at Controllable speech ("spoken quickly with a British accent"), research.. Self-inotarisirwa pa Free.ai GPUs - inofamba zvakasununguka pazuva rako re token pool (500 tokens per clip). Yakaburitswa pasi pe Apache 2.0 — kushandiswa kwekutengesa kwakabvumirwa pa Free.ai.
Usati washandisa
OpenAI-inowirirana REST API. Kugadzira chiratidzo uye kukumbira iyi model mumasekondi.
curl -X POST https://api.free.ai/v1/tts/ \
-H "Authorization: Bearer sk-free-..." \
-H "Content-Type: application/json" \
-d '{"model":"parler-tts-large","text":"hello world"}'Semuenzaniso mamodheru
Zvimwe zvinobvunzwa kakawanda
Parler-TTS Large inotsigira akawanda marudzi ezvinyorwa. Iyo yakazara runyorwa inoenderana nechirongwa; fomu pane iyi peji rinogamuchira chero tenzi uye chirongwa chinopa mavara ayo anotsigirwa. Ona /voice/ kune yakazara multi-engine picker kana iwe uchida chirongwa chechirongwa chine chirongwa chimwechete.
Zvizhinji zvema engines zvinopa chiGerman-American English sezvavanoita zvakajairika uye neakakodzera-ku-nzvimbo accent kune dzimwe nyika dzisingazivikanwe seEnglish.
SSML rutsigiro zvinosiyana ne engine. Pause, prosody, uye emphasis tags anozivikanwa pane akawanda premium injini uye pane mashoma self-hosted ones. Plain text anoshanda nguva dzose — hapana markup zvinodiwa.
Streaming TTS inowanikwa pa premium engines kuburikidza ne /v1/tts/ API endpoint ne stream=true. Web UI pane iyi peji inodzosera iyo yakazara clip mushure mekudzoka.
Parler-TTS Large inofamba paGPU yedu. Generation inotora kubva pazuva nezuva remahara pool. Kana richipera, zvinobhadharwa zvinotanga pa $5 → 200,000. Ruvara ~ 5 tokens per character, minimum 100 per clip.
Kusvika 5,000 mavara pazuva rewebhu UI. Kuti uwane zvinyorwa zvakakura (audiobooks, mabhuku akazara), shandisa /voice/audiobook/ izvo zvinowedzera uye zvinowedzera otomatiki, kana kuti tibate API munzira.
Yeah — POST a list of strings to /v1/tts/batch/, or use the workspace UI at /workspace/ to chain TTS into a longer pipeline (e.g., translate → speak → stitch).
Yes — POST text to /v1/tts/ with model="Parler-TTS Large" (or the slug on this page). Returns WAV or MP3. See /api/ for full reference + SDK snippets.
Kuzvidzora kwezwi (kuisa vhidhiyo) kunogona kuitwa ne /voice/clone/, asi izvi zvinoda kuti iwe ugare uine kodzero dzemutauro kana kuti uine mvumo yakanyorwa.
Zvimwe zvezvigadzirwa zvedu zvinopa masevhisi emhando yepamusoro, senge Free.ai-inozivikanwa GPUs; hapana chinodzokera kumaseva edu. Premium injini dzinopa masevhisi emhando yepamusoro pasi peDPA yedu.
Yega — Free.ai inokupa kodzero yekushandiswa kwezvinyorwa zvemavhidhiyo zvakagadzirwa neiyo engine. Iyo injini's license (Apache 2.0, MIT, kana mamiriro ekutengesa) inoratidzwa pamusoro peiyo model reference page; mukuita izvi zvinoreva kuti voiceovers, ads, podcasts, uye apps zvese zviri muchikamu ichi.
Yeah — kukundikana mabasa auto-refund kune chikonzero (zuva nezuva pool kana akabhadharwa tokens). Kana mari yekudzosera haasi kuoneka zuva rimwe chete, email contact@free.ai.