Waihoki AI Waihoki ki te kōrero
33+ ngā tauira pūtake tūwhera, 273+ ngā oro, 33+ Kāore he tatau e hiahiatia ana.
Ko ngā mea katoa e hiahiatia ana e koe mō te AI reo
30+ ngā utauta e whakahaeretia ana e ngā tauira pūtake tūwhera AI
33+ Kāhua reo AI
Ko te kohinga tino whānui o ngā tauira TTS pūtake tūwhera i roto i tētahi papatono
Kokoro Waihoki
Ko te Kokoro he tauira tuhi-ki-te-kōrero tauine 82 miriona e ātete ana i runga ake i tōna karaehe taumaha. Ahakoa tōna rahi iti, ka whakaputaina e ia he kōrero tino māori me te whakamārama. Ko te Kokoro e tautoko ana i ngā reo maha tae atu ki te reo Ingarihi, te reo Hapanihi, te reo Hainamana, me te reo Korean me ngā reo whakamārama maha. He tere rawa — e whakaputa ai i te oro tata ki te 100x tere ake i te wā tūturu i runga i te GPU.
Ko te tino pai mo: TTS whai hua nui me te ātete iti rawa, ngā taupānga rerenga
Whakamātautau wātea
Piper Waihoki
Ko Piper he mīhini kupu-ki-whakaahua ngāwari i hangaia e Rhasspy e whakamahi ana i ngā hanganga VITS me te larynx. E mahi ana katoa ana i runga i te CPU, e pai ana mō ngā pūrere pae, ngā pūkaha kāinga, me ngā taupānga e hiahiatia ana he TTS kāore i te tīariari. Me ngā reo neke atu i te 100 puta noa i ngā reo 30+, e tuku ana a Piper i te kōrero māori i te tere o te wā tūturu i runga anō i te Raspberry Pi 4.
Ko te tino pai mo: Ko ngā kitenga tere, ngā āheitanga, me ngā taupānga kōkuhu
Whakamātautau wātea
VITS Waihoki
VITS (He whakarerekētanga me te akoranga ātete mō te mutunga-ki-te mutunga o te kupu-ki-te-whakahaere) he aratuka TTS mutunga-ki-te mutunga e puta ai he pūoro māori ake i ngā tauira wāhanga-rua o nāianei, e whakaae ana ki te whakarerekētanga o te whakarerekētanga i whakanuia e ngā rerenga pūnoa me tētahi tukanga whakaakoranga ātete, e whiwhi ana i tētahi whakapainga nui i te mātauranga.
Ko te tino pai mo: Huinga ahuwhānui-tuhi-ki-te-kōrero me te pūāhua māori
Whakamātautau wātea
MeloTTS Waihoki
Ko MeloTTS e MyShell.ai he puna TTS reo maha e tautoko ana i te reo Ingarihi (American, British, Indian, Australian), Spanish, French, Chinese, Japanese, me te Korean. He tere rawa, e mahi ana i te kupu i te tere o te wā tūturu i runga i te CPU anake. Kua hangaia a MeloTTS mō te whakamahinga whakanao, ā, e tautoko ana i te CPU me te GPU.
Ko te tino pai mo: Ko ngā taupānga whakanao e hiahiatia ana he tere, he TTS reo maha
Whakamātautau wātea
Kani TTS 2 Waihoki
Kani-TTS-2 e NineNineSix he tauira tohutoro 400M tino māmā i hangaia ki runga i te pūtake LiquidAI LFM2 me te Nvidia NanoCodec. E haere ana i roto i te 3GB VRAM anake, ā, e whiwhi ana i ngā wā 10 o te kōrero i roto i ngā wā ~2 (RTF 0.2).
Ko te tino pai mo: He tere te whakawhanaketanga, ngā taiao rawa-iti, ngā tirohanga tere
Whakamātautau wātea
OuteTTS Waihoki
E whakaroa ana e te OuteTTS ngā tauira reo nui me ngā āheinga kupu-ki-whakaahua i te wā e pupuri ana i te hanganga taketake. E tautoko ana i ngā taupoki maha tae atu ki a llama.cpp (CPU/GPU), Hugging Face Transformers, ExLlamaV2, VLLM, ā, ko te whakawāteatanga whakangākau mā Transformers.js. He āhuahira te tārua reo kore-pōti mā ngā tātai kōrero i tiakina hei JSON.
Ko te tino pai mo: Whakapapatanga Edge, TTS i runga i te whakahura, taiao rawa-iti
Whakamātautau wātea
Pocket TTS Waihoki
Ko te Pocket TTS a Kyutai (ngā kaihanga o Moshi) he tauira kupu-ki-whakaahua 100M tauine-ki-whakaahua e whakarewa ana i runga ake i tōna taumahatanga. Ka mahi tika i runga i te CPU, e tautoko ana i te tārua reo kore-kōrero mai i tētahi tauira oro kotahi, ā, ka whakaputaina he kōrero māori. Ko te rahi o te tauira iti e tino pai ana mō te whakawhānui i te pito me ngā taiao rawa iti.
Ko te tino pai mo: Whakapapa māmā, taiao CPU- anake, whakaruru tere o te reo
Whakamātautau wātea
Kitten TTS Waihoki
Ko Kitten TTS e KittenML he tauira kupu-ki-rongo i hangaia ki runga i te ONNX. Me ngā tāupetanga mai i ngā tohu 15M ki te 80M (25-80 MB i runga i te pūrere), ka whakarato āhua pai o te reo i runga i te CPU me te kore e hiahiatia he GPU. He āhuahira 8 ngā reo i roto, te tere kōrero ā-ringa, me te whakatinana-tuhi i roto mō ngā tau, ngā moni, me ngā wae. He pai mō te whakawhānui i te pito me ngā taupānga iti-whakahaere.
Ko te tino pai mo: TTS tere, ngāwari, te whakawhānuitanga o te pito, ngā taupānga iti-latency
Whakamātautau wātea
Ming-Omni TTS Waihoki
Ming-omni-tts-0.5B e inclusionAI he tauira kōrero ā-waha-ā-waha i hangaia ki runga i te pūtake mārō o BailingMM me tētahi decoder oro-pātahitanga-pātahitanga. E tuku ana i te huaputa 44.1kHz (tata ki te āhuatanga CD), e tautoko ana i te tārua reo kore-kōrero mai i tētahi tohutoro 3+ tuarua, ā, kei roto hoki i te āhua o te āhua o te āhua / reo / BGM mā ngā tohutohu JSON. He pai rawa — 0.83% WER i ngā tohutoro Hainamana.
Ko te tino pai mo: He kōrero ā-rua-reo nui, he kōrero ā-waha, he ihirangi pukapuka oro Hainamana.
Whakamātautau wātea
MOSS-TTS Nano Waihoki
Ko te MOSS-TTS-Nano-100M te tāupetanga tauine 100M o te whānau MOSS-TTS o OpenMOSS, e tiritiri ana i te hoahoa whakarerekē-whakarerekē. E whakawhiti ana i te āhuatanga tiketike o te tauira 8B mō ngā taumahatanga ~80x iti iho me te VRAM iti iho i ia tono, e āhei ana ki ngā whakawhānuitanga wātea-wāhanga me te nui o te whakawhitinga.
Ko te tino pai mo: TTS-tīwae-whāiti, whakanaotanga nui-kitenga, whakamahinga whakawhitiwhitinga iti-whakahaere
Whakamātautau wātea
Bark Pa_mu
He tauira kupu-ki-rongoā i runga anō i te whakarerekētanga e puta ai te kōrero pono, te pūoro, me ngā pānga oro.
kaiwhakawhanake: Suno · Whakawhiwhinga: MIT
Ka whakamātautau
Bark Small Pa_mu
Ko te putanga māmā ake o Bark me te whakawāteatanga tere ake me te whakamahinga pūmahara iti iho.
kaiwhakawhanake: Suno · Whakawhiwhinga: MIT
Ka whakamātautau
CosyVoice 2 Pa_mu
Ka taea e Alibaba te whakawhānui i te TTS me te āhua o te tangata me te tata ki te kore.
kaiwhakawhanake: Alibaba (Tongyi Lab) · Whakawhiwhinga: Apache 2.0
Ka whakamātautau
Dia TTS Pa_mu
He tauira whakawhanake kōrerorero maha e waihanga ana i ngā kōrero māori i waenganui i ngā kaikōrero.
kaiwhakawhanake: Nari Labs · Whakawhiwhinga: Apache 2.0
Ka whakamātautau
Parler TTS Pa_mu
E whakaahua ana i te reo e hiahiatia ana e koe i roto i te reo māori, ā, ka whakaputaina e te Parler he kōrero ōrite.
kaiwhakawhanake: Hugging Face · Whakawhiwhinga: Apache 2.0
Ka whakamātautau
IndexTTS-2 Pa_mu
Zero-shot TTS me te mana ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā
kaiwhakawhanake: Index Team · Whakawhiwhinga: Bilibili Model License
Ka whakamātautau
Spark TTS Pa_mu
Ko te tārua reo TTS me te āhua kōrero me te āhua kōrero e whakahaeretia ana mā ngā whakahau.
kaiwhakawhanake: SparkAudio · Whakawhiwhinga: CC BY-NC-SA 4.0
Ka whakamātautau
GPT-SoVITS Pa_mu
He iti noa iho te tārua reo TTS e tārua ana i tētahi reo mai i te 5 waeine o te oro.
kaiwhakawhanake: RVC-Boss · Whakawhiwhinga: MIT
Ka whakamātautau
Orpheus Pa_mu
I whakaakona te tauira TTS ā-āhua tangata i runga i ngā wā 100K o ngā raraunga kōrero.
kaiwhakawhanake: Canopy Labs · Whakawhiwhinga: Llama 3.2 Community
Ka whakamātautau
Qwen3 TTS Pa_mu
Ko te TTS maha-reo a Alibaba me te tārua reo, ngā reo i whakaritea, me te hoahoa reo mai i te kupu.
kaiwhakawhanake: Alibaba (Qwen) · Whakawhiwhinga: Apache 2.0
Ka whakamātautau
VieNeu-TTS-v2 Pa_mu
Vietnam + TTS whakarerekē-waehere Ingarihi me ngā oro 7 i whakaritea i mua me te tārua reo kore-kore. CPU- anake, kāore e hiahiatia ana he GPU.
kaiwhakawhanake: Phạm Nguyễn Ngọc Bảo · Whakawhiwhinga: Apache 2.0
Ka whakamātautau
Chatterbox Turbo Pa_mu
He tere ake te Chatterbox me te ātetetanga iti iho i te 200ms me ngā tohu ā-reo mō te pōhēhē, te poapoa, me ētahi atu.
kaiwhakawhanake: Resemble AI · Whakawhiwhinga: MIT
Ka whakamātautau
VoxCPM Pa_mu
Ko te TTS kore tohu e whakanao ana i te oro 44.1kHz me te ōritetanga o te wāhanga mātauranga horopaki.
kaiwhakawhanake: OpenBMB · Whakawhiwhinga: Apache 2.0
Ka whakamātautau
VibeVoice Pa_mu
He tauira a Microsoft mō ngā ihirangi kōrero maha o te āhua roa pēnei i ngā podcast me ngā pukapuka oro.
kaiwhakawhanake: Microsoft · Whakawhiwhinga: MIT
Ka whakamātautau
CosyVoice3 Pa_mu
Next-generation multilingual TTS with bi-streaming, emotion control, and zero-shot voice cloning.
kaiwhakawhanake: Alibaba (FunAudioLLM) · Whakawhiwhinga: Apache 2.0
Ka whakamātautau
NAMAA Saudi TTS Pa_mu
TTS tuatahi i whakatuwheratia e Saudi-Arabic. Ka taea e te reo māori o Saudi te tārua reo ā-whakahaere.
kaiwhakawhanake: NAMAA Space · Whakawhiwhinga: MIT
Ka whakamātautau
Darwin TTS Pa_mu
Ko te tāupetanga Qwen3-TTS whakawhiti-whakahaere me ngā taumahatanga FFN i whakakotahitia mai i te tauira reo Qwen3-1.7B mō te tārua reo maha kē atu.
kaiwhakawhanake: FINAL-Bench · Whakawhiwhinga: Apache 2.0
Ka whakamātautau
MOSS-TTSD Pa_mu
He tauira haere tonu o te kōrerorero maha - ka whakaputaina he kōrerorero āhua podcast tae atu ki ngā kaikōrero e 5 me ngā minu 60 o te oro whakarongo.
kaiwhakawhanake: OpenMOSS · Whakawhiwhinga: Apache 2.0
Ka whakamātautau
Chatterbox Whakahauhau
Ko te tāruatanga reo ā-kore o te āhua o te āhua me te mana ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā.
Kāwai:
Ka whakamātautau
Tortoise TTS Whakahauhau
E arotahi ana te kupu-ki-te-reo-maha ki te āhuatanga me te hoahoa anō.
Kāwai:
Ka whakamātautau
StyleTTS 2 Whakahauhau
Ko te tuhituhi-ki-te-kōrero o te taumata tangata mā te whakawhānuitanga o te kāhua me te whakaakoranga ātete.
Kāwai:
Ka whakamātautau
OpenVoice Whakahauhau
Kātahi anō ka tārua te reo me te mana ā-waha i runga i te kāhua, te āhuahira, me te āhuahira.
Kāwai:
Ka whakamātautau
Sesame CSM Whakahauhau
He tauira kōrero kōrero e whakaputa ana i tētahi kōrero māori me te wā me te āhua tika.
Kāwai:
Ka whakamātautauCosyVoice 2
Ka taea e Alibaba te whakawhānui i te TTS me te āhua o te tangata me te tata ki te kore.
reo: en, zh, ja, ko, fr, de, it, es
Pāpāho te reoIndexTTS-2
Zero-shot TTS me te mana ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā
reo: en, zh
Pāpāho te reoSpark TTS
Ko te tārua reo TTS me te āhua kōrero me te āhua kōrero e whakahaeretia ana mā ngā whakahau.
reo: en, zh
Pāpāho te reoGPT-SoVITS
He iti noa iho te tārua reo TTS e tārua ana i tētahi reo mai i te 5 waeine o te oro.
reo: en, zh, ja, ko
Pāpāho te reoChatterbox
Ko te tāruatanga reo ā-kore o te āhua o te āhua me te mana ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā-ā.
reo: en
Pāpāho te reoTortoise TTS
E arotahi ana te kupu-ki-te-reo-maha ki te āhuatanga me te hoahoa anō.
reo: en
Pāpāho te reoOpenVoice
Kātahi anō ka tārua te reo me te mana ā-waha i runga i te kāhua, te āhuahira, me te āhuahira.
reo: en, zh, ja, ko, fr, es
Pāpāho te reoVieNeu-TTS-v2
Vietnam + TTS whakarerekē-waehere Ingarihi me ngā oro 7 i whakaritea i mua me te tārua reo kore-kore. CPU- anake, kāore e hiahiatia ana he GPU.
reo: vi, en
Pāpāho te reoChatterbox Turbo
He tere ake te Chatterbox me te ātetetanga iti iho i te 200ms me ngā tohu ā-reo mō te pōhēhē, te poapoa, me ētahi atu.
reo: en
Pāpāho te reoVoxCPM
Ko te TTS kore tohu e whakanao ana i te oro 44.1kHz me te ōritetanga o te wāhanga mātauranga horopaki.
reo: en, zh
Pāpāho te reoOuteTTS
TTS i runga i te LLM e haere ana i runga i te CPU, GPU, te whakataki rānei mā te llama.cpp me Transformers.js.
reo: en
Pāpāho te reoPocket TTS
He tauira māmā 100M te tauira tauwhāinga a Kyutai me te tārua reo mai i tētahi tauira kotahi.
reo: en, fr
Pāpāho te reoCosyVoice3
Next-generation multilingual TTS with bi-streaming, emotion control, and zero-shot voice cloning.
reo: en, zh, ja, ko, de, es, fr, it, ru
Pāpāho te reoNAMAA Saudi TTS
TTS tuatahi i whakatuwheratia e Saudi-Arabic. Ka taea e te reo māori o Saudi te tārua reo ā-whakahaere.
reo: ar
Pāpāho te reoDarwin TTS
Ko te tāupetanga Qwen3-TTS whakawhiti-whakahaere me ngā taumahatanga FFN i whakakotahitia mai i te tauira reo Qwen3-1.7B mō te tārua reo maha kē atu.
reo: en, ko, ja, zh
Pāpāho te reoMOSS-TTSD
He tauira haere tonu o te kōrerorero maha - ka whakaputaina he kōrerorero āhua podcast tae atu ki ngā kaikōrero e 5 me ngā minu 60 o te oro whakarongo.
reo: en, zh
Pāpāho te reoMing-Omni TTS
He tauira kōrero ā-waha 0.5B ngāwari mai i te whakaurunga AI me te huaputa 44.1kHz me te tārua reo kore.
reo: en, zh
Pāpāho te reoMOSS-TTS Nano
He iti iho te momo 100M MOSS-TTS — he āhuahanga ōrite, he iti iho te 80x, he wātea wātea-wāhanga.
reo: en, zh, de, es, fr, ja, it, ko, ru, ar, pt
Pāpāho te reoKa tīmata te API o te kaiwhakawhanake
REST API e ōrite ana ki OpenAI. Kotahi te wāhi mutunga, 22+ ngā tauira. Whakawhiwhinga tautoko mō ngā taupānga wā tūturu.
- He hanga e ōrite ana ki te OpenAI
- TTS Streaming mō ngā taupānga wā tūturu
- Ko te tukanga rōpū mō ngā mahi nui
- Whakawatanga Webhook
pip install ttsai
npm install @ttsainpm/ttsai
from tts_ai import TTSClient
client = TTSClient(api_key="sk-tts-xxx")
audio = client.generate(
text="Hello from TTS.ai!",
model="kokoro",
voice="af_bella",
)
client.save(audio, "output.mp3")He ngāwari, he mārama te utu
Ka tīmata wātea. Tauine i a koe e tipu ana.
Waihoki
15,000 ngā āhuatanga + 5,000/rohe
- 7 ngā tauira wātea tae atu ki a Kokoro
- 5,000 ngā pūāhua i ia whakatupuranga
- Kei roto te urupare API
Ka tīmata
500 ngā pūtea/whā
- 22+ ngā tauira katoa
- 100,000 ngā pūāhua i ia whakatupuranga
- Ko te tāruatanga reo
Pro
2,000 ngā pūtea/whā
- Ko nga mea katoa i roto i te Starter
- Ka uru ki te API
- Whakahaeretanga aronga
Waihoki
10,000 ngā pūtea/whā
- Ko nga mea katoa i roto i Pro
- Bulk API
- Tauwhāinga tūnga
E pā ana ngā pātai
He aha ka taea e tātau te whakapai ake? Ka āwhina tātau ki te whakaoti i ngā raruraru.
Ka tīmata ki te whakamahi i te reo AI i tēnei rā
E hono ana ki ngā kaiwhakanao, ngā kaiwhakawhanake, me ngā umanga mā te whakamahi i te TTS.ai