Qoraalka asalka ah ee qoraalka ah
MIT, Apache 2.0 — ma jiro xarig-in, ma jiro xaddidaadyo isticmaalka, ma jiro lacagaha liisan-qaadista oo la yaab leh. Ku isticmaal API-ga aan martigelinno, ama iyaga oo ku martiqaada dhismahaada oo leh xakamayn buuxda.
Ku day
Faa'iidooyinka Open Source TTS
Maxaa sabab u ah qaababka asalka furan ee mashruucyadaada
Dhammaan Open-Source Licensed
Mid kasta oo ka mid ah TTS.ai wuxuu isticmaalaa liisan furan oo furan. Ma jiro booqo madow oo gaar ah, ma jiro xirmo iibiyaha, ma jiro lacag liisan oo aan la filayn.
MIT / Apache 2. 0
Models waa la siiyay ogolaansho hoos MIT ama Apache 2.0, ugu badan ee ogolaansho furan-source licenses. isticmaal ganacsi, bedeli, dib u qaybinta — xaddidaad la'aan.
Is-hoosaysiinta
Soo dejisan nooc kasta oo ah oo ku socda qalabkaaga. Xukunka buuxa ee xogtaada, latentity, iyo dhismayaasha.
GPU-ga ugufiican
Models waa ugu fiican ee NVIDIA GPUs la taageerada CUDA. Piper ku socda CPU kaliya. Models badankoodu waxay u baahan yihiin 2-8GB VRAM si loo hubiyo in ay wax ku ool ah.
Bulshada la ilaaliyo
Bulshooyinka furan ee furan ayaa ilaaliya oo hagaajiya moodooyinkan. Ka qaybgalku waa soo dhaweynayaa - soo gudbi bugs, hagaajinta, iyo codadka cusub ee GitHub.
Isticmaal Ganacsi OK
Waxyaabaha dhisa, adeegyada iibinta, iyo abuuro content ganacsi la'aan royalties ama kharashka isticmaalka.
Our Open Source Model Catalog
Mid kasta oo ka mid ah, liisankiisa, iyo waxa ay ugu fiican tahay
Kokoro
Free
Lightweight 82M parameter model delivering studio-quality speech with blazing-fast inference.
Ugu Fiican: Apache 2.0 — qiimaha ugu fiican ee bilaashka ah, 82M params, fududahay in la isku martiqaado
Daawo Kokoro
Piper
Free
A fast, local neural text to speech system optimized for Raspberry Pi and embedded devices.
Ugu Fiican: MIT - CPU-keliya, oo ku habboon aaladaha cidhifka ah iyo martigelinta is-hoosaysiinta
Daawo Piper
VITS
Free
Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech.
Ugu Fiican: MIT — dhismaha foundational loo isticmaalo by qaar badan oo ka hooseeya qaabab
Daawo VITS
Bark
Standard
Transformer-based text-to-audio model that generates realistic speech, music, and sound effects.
Ugu Fiican: MIT — awoodaha audio dhalasho gaar ah ka baxsan TTS caadiga ah
Daawo Bark
Tortoise TTS
Premium
Multi-voice text-to-speech focused on quality with autoregressive architecture.
Ugu Fiican: Apache 2.0 — tayada ugu badan, si ballaaran u barteen fulinta tixgelin
Daawo Tortoise TTS
OpenVoice
Premium
Instant voice cloning with granular control over style, emotion, and accent.
Ugu Fiican: MIT — soo-saarka codka furan oo leh xakamaynta qaabka granular
Daawo OpenVoiceSida loo isticmaalo Open Source TTS
isticmaal API-ga aan martigelinno ama ku rakib moodooyinka adiga oo keliya
Ka fiirso qaababka asalka furan
Booqo catalogkeena 20+ open-source TTS qaabab. Model page kasta oo muujinaya liisan, dhisme, awoodaha, iyo shuruudaha self-hosting.
Ku raaxayso Browser-kaaga
Tijaabi nooc kasta oo si toos ah ku saabsan TTS.ai aan waxba ku rakibin. Server-yada GPU-ga ayaa wax ka qaban kara habka si aad u qiimeyso tayada ka hor intaadan u diyaarin inaad iska diiwaangeliso.
Self-Host ama isticmaal API-keena
Ku dheji moodooyinka GitHub iyo ku rakib gudaha, ama isticmaal API-ga aan martigelinno ee wax soo saarka. Self-hosting wuxuu siiyaa xakamayn buuxda; API-keena wuxuu siiyaa dhisme la maamulo.
Dhis codsigaaga
TTS ku darto alaabtaada adigoo isticmaalaya qaababkaaga ama API-ga REST. Qaababka dhammaantood waa kuwo ganacsi loo isticmaali karo oo aan lahayn lacagaha liisan ama hantida.
Lacag-bixiye
dhammaan noocyada ku saabsan TTS.ai isticmaalaan sharciyada ganacsiga-friendly furan-source
| Nooc | Liisan | Waxqabadka Ganacsi | Isbeddel | Guriga-isaga-u-soo-dhaweynta | Adeegsiga |
|---|---|---|---|---|---|
| Kokoro | Apache 2.0 | Waa in la buuxiyaa | |||
| Piper | MIT | ikhtiyaari | |||
| VITS | MIT | ikhtiyaari | |||
| MeloTTS | MIT | ikhtiyaari | |||
| Chatterbox | MIT | ikhtiyaari | |||
| Tortoise TTS | Apache 2.0 | Waa in la buuxiyaa | |||
| StyleTTS 2 | MIT | ikhtiyaari | |||
| OpenVoice | MIT | ikhtiyaari | |||
| Sesame CSM | Apache 2.0 | Waa in la buuxiyaa | |||
| Orpheus | Llama 3.2 | "Built with Llama" |
Self-Hosting vs Hosted API
Run qaabab adiga oo kale ama noo oggolaan in ay maamulaan dhismaha
Self-Host on Your Hardware
Mid kasta oo ka mid ah TTS.ai oo ku yaal waxaa laga heli karaa sidii mashruuc furan oo ku yaal GitHub ama Hugging Face. Soo deji miisaanka, ku rakib ku xiran, oo ku rakib tijaabinta GPU-yadaada. Waxaad leedahay xakamayn buuxda oo ku saabsan latentity, gaarka ah, iyo kala-soocidda.
- Xogta gaarka ah ee buuxda - audio marnaba ma ka tago server
- Ma jiraan per-dalbaday kharashka ka dib markii setup hore
- Custom fine-tuning on your data gaar ah
- U baahan yahay qalabka GPU (NVIDIA ayaa lagula talinayaa)
- Waxaad maamuli kartaa cusbooneysiinta, kordhinta, iyo ku tiirsanaanta
isticmaal TTS.ai Hosted API
Ka hel helitaanka degdegga ah ee dhammaan 20+ moodooyinka iyada oo loo marayo API REST kaliya. Waxaan maamulnaa GPU provisioning, cusbooneysiin moodel, maareynta fariinta, iyo ballaadhinta. Mid ka mid ah API-ga ayaa kuu oggolaanaya inaad gasho moodel kasta - ma jirto baahi loo qabo maareynta soo bandhigid kala duwan.
- Ma jiro hardware GPU loo baahan yahay
- Dhammaan 20+ qaabab ka mid ah API
- Automatic model cusbooneysiin iyo horumarinta
- 99.9% uptime la dhismaha dheeraad ah
- Bixi oo kaliya waxa aad isticmaali
Bilow degdeg ah: API ama Self-Host
isticmaal API-ga aan martigelinno, ama ku rakib Kokoro gudaha daqiiqado
import requests
response = requests.post("https://api.tts.ai/v1/tts", json={
"text": "Open source TTS with a simple API.",
"model": "kokoro",
"voice": "af_heart",
"format": "wav"
}, headers={"Authorization": "Bearer YOUR_API_KEY"})
with open("output.wav", "wb") as f:
f.write(response.content)# Install Kokoro locally
pip install kokoro
# Generate speech on your own GPU
import kokoro
pipeline = kokoro.KPipeline(lang_code="a")
generator = pipeline("Hello from your own server!", voice="af_heart")
for i, (gs, ps, audio) in enumerate(generator):
kokoro.save(audio, f"output_{i}.wav")Open Source, Qiimaha lacagta
API-keena martida ah wuxuu ka dhigayaa TTS-ka furan ee furan oo aan la maamulin GPUs.
Tallaabada bilaashka ah
$0
15,000 xaraf oo ku saabsan diiwaangelinta
- 4 qaabab furan oo bilaash ah
- Ma jiro diiwaangelinta isticmaalka asalka ah
- isticmaalka ganacsi ee la oggol yahay
Bilow
$9
500,000 xaraf / bilood
- Dhammaan 20+ qaababka asalka furan
- Duubista Codka
- API access
Pro
$29
2,000,000 xaraf / bilood
- Horumarinta GPU
- dhammaan noocyada premium
- taageero Enterprise
Su'aalaha badanaa la waydiiyo
Su'aalaha caadiga ah ee ku saabsan qoraalka qoraalka ah ee qoraalka ah
Maxaa aan ku hagaajin karnaa? Jawaabtaada waxay naga caawisaa inaan xallino dhibaatooyinka.
Ka raadi Open Source TTS maanta
20+ qaabab furan oo furan, dhammaantood ganacsi-liisan. U isticmaal API-keena ama martigelinta-gaaban - doorashadu waa adiga.