Ka tūwhera te pūtake o te kupu ki ngā tauira kōrero
He pūtake tūwhera ia tauira TTS i runga i tātau papa, ā, ko te nuinga o te whakamahi i te MIT, Apache rānei 2.0. He torutoru ngā tauira me ngā reo kua whakawhiwhia ki te whakamahinga kāore i te hokohoko anake, ā, kua tohutia 'Ko te whakamahinga whaiaro me te kore hokohoko anake'. Ka whakamahia i roto i tātau API hopu, ka whakawhiwhia rānei ki tō rātou ake hanganga me te whakahaere katoa.
Ka whakamātautia ināianei
Ko nga painga o te pūtake tūwhera TTS
He aha te tikanga o ngā tauira pūtake tūwhera mō ōna kaupapa?
Ko nga mea katoa kua whakaaetia e te pūtake tūwhera
He pūtake tūwhera ia tauira i runga i te TTS.ai, ā, ko ia pātaka tauira e whakarārangi ana i tōna raina. Kāore he kāwai mārō, kāore he kati kaipāpāho.
Whakawhiwhinga pūtake tūwhera
Ko te nuinga o ngā tauira kua whakawhiwhia ki raro i te MIT, Apache rānei 2.0. He torutoru e whakamahi ana i ētahi atu whakawhiwhinga, ā, ko ngā tauira, ngā reo rānei i whakawhiwhia ki te whakamahi kāore i te hokohoko, kua tohutia "Ko te whakamahinga whaiaro me te kore hokohoko anake".
Kātahi anō ka whakahohe
Ka whakataki i tētahi tauira me te whakahaere i ia i runga i ōna ake pūrere. Ka tino whakahaeretia ōna raraunga, te ātetetanga, me te hanganga. Kāore e hiahiatia te whakawhirinaki ki te mātao.
Kua pai ake te GPU
Kua whakaritea ngā tauira mō ngā GPU NVIDIA me te tautoko CUDA. Ka haere a Piper i runga i te CPU anake. E hiahiatia ana e te nuinga o ngā tauira he 2–8GB VRAM mō te whakawāteatanga mātauranga.
Ko te iwi i pupuritia
Ko ngā rōpū pūtake tūwhera hohe e pupuri ana, e whakarei ake ana hoki i ēnei tauira. E whakaaetia ana ngā koha — e tono ana i ngā hapa, ngā whakapainga, me ngā reo hōu i runga i te GitHub.
Tērā te raina hokohoko e wātea ana
Ko tētahi kaupapa utu mai i te $5/mo e mau ana i te raina hokohoko mō ngā mea e waihanga ana, kāore he utu, he utu whakamahinga rānei; ko te taumata wātea mō te whakamahinga whaiaro. Ko ngā tauira me ngā reo i tohutia "Ko te whakamahinga whaiaro me te kore-whakaahua anake" e whakawāteatia ana.
Ko tātau pukapuka tauira pūtake tūwhera
He tauira ia tauira, tōna whakaaetanga, me te mea pai rawa e mahi ai.
Kokoro
Free
Lightweight 82M parameter model delivering studio-quality speech with blazing-fast inference.
Ko te tino pai mo: Apache 2.0 — te tauira wātea pai rawa, 82M ngā tohu, he ngāwari ki te whakanoho i a ia anō
Whakamātautau Kokoro
Piper
Free
A fast, local neural text to speech system optimized for Raspberry Pi and embedded devices.
Ko te tino pai mo: MIT — CPU- anake, tino pai mo ngā pūrere perehitini me te whakahoahoa ā-hinengaro
Whakamātautau Piper
VITS
Free
Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech.
Ko te tino pai mo: MIT — te hanganga taketake e whakamahia ana e ngā tauira maha o raro.
Whakamātautau VITS
Bark
Standard
Transformer-based text-to-audio model that generates realistic speech, music, and sound effects.
Ko te tino pai mo: MIT — ngā āheinga whakanao oro motuhake i tua atu i te TTS paerewa
Whakamātautau Bark
Tortoise TTS
Premium
Multi-voice text-to-speech focused on quality with autoregressive architecture.
Ko te tino pai mo: Apache 2.0 — te pai rawa, te whakatinanatanga tohutoro whānui i akona
Whakamātautau Tortoise TTS
OpenVoice
Premium
Instant voice cloning with granular control over style, emotion, and accent.
Ko te tino pai mo: MIT — te tārua reo pūtake tūwhera me te whakahaere kāhua matatini
Whakamātautau OpenVoiceHe pēhea te whakamahi i te pūtake tūwhera TTS
Ka whakamahia tātau te API kaihautū, ka whakahaere rānei i ngā tauira ki a koe
E torotoro ana i ngā tauira pūtake tūwhera
Ka tirohia tātau pukapuka o ngā tauira TTS pūtake tūwhera 20+. Ka whakaaturia e ia pātū tauira te whakaaetanga, te hanganga, ngā āheinga, me ngā whakaritenga whakahoahoa.
Ka whakamātau i roto i tō tou kaitirotiro
Whakamātautau i tētahi tauira hāngai i runga i te TTS.ai me te kore whakatū i tētahi mea. Ka whakahaeretia e a tātau pūnaha GPU te tukanga kia taea ai e koe te arotake i te kounga i mua i te whakawhiwhinga ki te whakawhiwhinga.
Māna-māna, Ka whakamahia rānei tātau API
Ko te tārua o ngā tāurunga tauira mai i te GitHub me te whakahaere ā-rohe, te whakamahi rānei i tātau API kaihautū mō te whakanaotanga. Ka hoatu e te kaihautū anō te mana katoa; Mā tātau API e whakarato ana i te hanganga whakahaere.
Hanganga i ōna taupānga
Ko te whakauru i te TTS ki roto i tōna hua mā te whakamahi i ngā tauira anō, i a tātau rānei REST API. Ka tirohia i te tuatahi ia raina tauira: he torutoru ngā tauira me ngā reo mō te whakamahinga kāore i te hokohoko anake.
Tērā te whakataurite waehere
Te raihana o ia tauira i runga i te TTS.ai
| Kāhua | Whakawhiwhinga | Ka whakamahia ki te hokohoko | Ka whakakētia | Māmā te kaihautū | Whakawhiwhinga |
|---|---|---|---|---|---|
| Kokoro | Apache 2.0 | E hiahiatia ana | |||
| Piper | MIT He rerekē te mīhini; he rerekē ngā raina reo | Ko ētahi oro anake | Ka taea | ||
| VITS | MIT | Ka taea | |||
| MeloTTS | MIT | Ka taea | |||
| Chatterbox | MIT | Ka taea | |||
| Tortoise TTS | Apache 2.0 | E hiahiatia ana | |||
| StyleTTS 2 | MIT | Ka taea | |||
| OpenVoice | MIT | Ka taea | |||
| Sesame CSM | Apache 2.0 | E hiahiatia ana | |||
| Orpheus | Llama 3.2 | "Built with Llama" | |||
| Spark TTS | CC BY-NC-SA 4.0 | Ko te whakamahinga whaiaro me te kore-whakaahua anake | E hiahiatia ana | ||
| OuteTTS | CC BY-NC-SA 4.0 | Ko te whakamahinga whaiaro me te kore-whakaahua anake | E hiahiatia ana |
Hopu vs Hosted API
Ka whakahaere i ngā tauira koe, ka whakaae rānei kia whakahaeretia e tātau te hanganga
Māna anō te kaihautū i runga i ōna pūrere
Kei te wātea ia tauira i runga i te TTS.ai hei kaupapa pūtake tūwhera i runga i te GitHub, i te Hugging Face rānei. Whakataki i ngā taumahatanga, te whakatū i ngā whakawhirinaki, me te whakahaere i te whakawāteatanga i runga i ōna GPU ake. He mana katoa tātou i runga i te ātetetanga, te ātetetanga, me te tauinetanga.
- Ko te ātetetanga raraunga katoa — kāore te oro i tae atu ki tōna pūnaha
- Kāore he utu-i-te tono i muri i te whakaritenga tuatahi
- He tino tika te whakarerekētanga i runga i ōna raraunga
- E hiahiatia ana ngā pūrere GPU (e whakaritea ana e NVIDIA)
- Ka whakahaeretia e koe ngā whakahōutanga, te tauine, me ngā whakawhirinaki
Ka whakamahia te TTS.ai Hosted API
Ka whiwhi āheitanga tere ki ngā tauira 20+ katoa mā tētahi API REST kotahi. Ka whakahaeretia e tātau te GPU, ngā whakahōutanga tauira, te whakahaere kōwae, me te tauinetanga. Ko te kī API kotahi e whakarato ana i te āheitanga ki ia tauira — kāore e hiahiatia kia whakahaeretia ngā whakawhānuitanga motuhake.
- Kāore he rauemi GPU e hiahiatia ana
- 20+ ngā tauira katoa mā te API kotahi
- Whakahōutanga tauira me ngā whakapainga
- 99.9% uptime me te hanganga nui rawa
- Ko te utu anake mo te mea e whakamahia ana e koe
Ka tīmata tere: API, Māna rānei te kaihautū
Ka whakamahia tātau te API kaihautū, ka whakatū ā-rohe rānei a Kokoro i roto i ngā minu
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")Māmā te pūtake, te utu ā-ringa
Ka taea e tātau te hopu i te TTS pūtake tūwhera me te kore whakahaere i ngā GPUs.
Waihoki
$0
50 ngā pūtea i te whakaingoatanga
- 4 ngā tauira pūtake tūwhera
- Kāore he whakaingoatanga mō te whakamahinga taketake
- Ko te whakamahinga whaiaro, kāore i te hokohoko
Ka tīmata
$9
500 ngā pūtea/whā
- 20+ ngā tauira pūtake tūwhera katoa
- Ko te tārua reo
- Ka uru ki te API
Pro
$29
2000 ngā pūtea/whā
- Whakahaeretanga GPU arotahi
- Ko nga tauira katoa
- Mā te tautoko pāpori
E pā ana ngā pātai
Ko ngā pātai noa iho mo te kupu pūtake tūwhera ki te kōrero
He aha ka taea e tātau te whakapai ake? Ka āwhina tātau ki te whakaoti i ngā raruraru.
Whakamātau i te pūtake tūwhera TTS i tēnei rā
20+ ngā tauira pūtake-mārō, ko ia me tōna raina i whakarārangitia. Ka whakamahia tātau API, te kaihautū-kore rānei, ko te kōwhiringa ko tātau.