Tasuta tehisintellekt Tekst kõnele
22+ avatud lähtekoodiga mudelid, 100+ hääled, 32+ keeli. Kontot ei ole vaja.
Kõik, mida vajate hääl AI
24+ avatud lähtekoodiga tehisintellektimudelitel töötavad 26 tööriista
22+ AI häälemudelid
Kõige ulatuslikum avatud lähtekoodiga TTS-mudelite kogu ühes platvormis
Kokoro Free
Kokoro is an 82 million parameter text-to-speech model that punches well above its weight class. Despite its tiny size, it produces remarkably natural and expressive speech. Kokoro supports multiple languages including English, Japanese, Chinese, and Korean with a variety of expressive voices. It runs incredibly fast — generating audio nearly 100x faster than real-time on a GPU.
Parim: High-quality TTS with minimal latency, streaming applications
Proovi tasuta
Piper Free
Piper is a lightweight text-to-speech engine developed by Rhasspy that uses VITS and larynx architectures. It runs entirely on CPU, making it ideal for edge devices, home automation, and applications requiring offline TTS. With over 100 voices across 30+ languages, Piper delivers natural-sounding speech at real-time speeds even on a Raspberry Pi 4.
Parim: Quick previews, accessibility, and embedded applications
Proovi tasuta
VITS Free
VITS (Variational Inference with adversarial learning for end-to-end Text-to-Speech) is a parallel end-to-end TTS method that generates more natural sounding audio than current two-stage models. It adopts variational inference augmented with normalizing flows and an adversarial training process, achieving a significant improvement in naturalness.
Parim: General-purpose text-to-speech with natural prosody
Proovi tasuta
MeloTTS Free
MeloTTS by MyShell.ai is a multilingual TTS library supporting English (American, British, Indian, Australian), Spanish, French, Chinese, Japanese, and Korean. It is extremely fast, processing text at near real-time speed on CPU alone. MeloTTS is designed for production use and supports both CPU and GPU inference.
Parim: Tootmisrakendused, mis vajavad kiiret mitmekeelset TTS-d
Proovi tasuta
Bark Standard
Transformer-based text-to-audio model that generates realistic speech, music, and sound effects.
Arendaja: Suno · Litsents: MIT
Proovi seda.
Bark Small Standard
Lighter version of Bark with faster inference and lower memory usage.
Arendaja: Suno · Litsents: MIT
Proovi seda.
CosyVoice 2 Standard
Alibaba's scalable streaming TTS with human-parity naturalness and near-zero latency.
Arendaja: Alibaba (Tongyi Lab) · Litsents: Apache 2.0
Proovi seda.
Dia TTS Standard
Mitme kõlariga dialoogi genereerimise mudel, mis loob kõnelejate vahel loomuliku vestluse.
Arendaja: Nari Labs · Litsents: Apache 2.0
Proovi seda.
Parler TTS Standard
Describe the voice you want in natural language and Parler generates matching speech.
Arendaja: Hugging Face · Litsents: Apache 2.0
Proovi seda.
IndexTTS-2 Standard
Zero-shot TTS with fine-grained emotion control and high expressiveness.
Arendaja: Index Team · Litsents: Apache 2.0
Proovi seda.
Spark TTS Standard
Voice cloning TTS with controllable emotion and speaking style via prompts.
Arendaja: SparkAudio · Litsents: Apache 2.0
Proovi seda.
GPT-SoVITS Standard
Few-shot voice cloning TTS that replicates any voice from just 5 seconds of audio.
Arendaja: RVC-Boss · Litsents: MIT
Proovi seda.
Orpheus Standard
Human-level emotional TTS model trained on 100K hours of speech data.
Arendaja: Canopy Labs · Litsents: Llama 3.2 Community
Proovi seda.
Qwen3 TTS Standard
Alibaba's multilingual TTS with voice cloning, preset voices, and voice design from text.
Arendaja: Alibaba (Qwen) · Litsents: Apache 2.0
Proovi seda.
CosyVoice 2
Alibaba's scalable streaming TTS with human-parity naturalness and near-zero latency.
Keeled: en, zh, ja, ko, fr, de, it, es
Klooni hääl
IndexTTS-2
Zero-shot TTS with fine-grained emotion control and high expressiveness.
Keeled: en, zh
Klooni hääl
Spark TTS
Voice cloning TTS with controllable emotion and speaking style via prompts.
Keeled: en, zh
Klooni hääl
GPT-SoVITS
Few-shot voice cloning TTS that replicates any voice from just 5 seconds of audio.
Keeled: en, zh, ja, ko
Klooni hääl
Chatterbox
"State-of-the-art null-shot hääl kloonimine emotsioonide kontrolli Remonte AI.
Keeled: en
Klooni hääl
Tortoise TTS
Mitme häälega teksti kõne-kõne keskendus kvaliteedi autoregressiivne arhitektuur.
Keeled: en
Klooni hääl
OpenVoice
Kiire hääl kloonimine granuleeritud kontrolli stiil, emotsioonid, ja aktsent.
Keeled: en, zh, ja, ko, fr, de, es, it
Klooni hääl
Qwen3 TTS
Alibaba's multilingual TTS with voice cloning, preset voices, and voice design from text.
Keeled: en, zh, ja, ko, de, fr, ru, pt, es, it
Klooni häälArendaja- esimene API
OpenAI ühilduv REST API. Üks tulemusnäitaja, 22+ mudelid. Streaming toetust reaalajas rakendusi.
- OpenAI- ga ühilduv vorming
- Trimmimine TTS reaalajas rakendused
- Partii töötlemine suurte tööde jaoks
- Veebikonksu teated
import requests
response = requests.post(
"https://api.tts.ai/v1/tts/",
headers={"Authorization": "Bearer sk-tts-xxx"},
json={
"model": "kokoro",
"text": "Hello from TTS.ai!",
"voice": "af_bella",
}
)
with open("output.mp3", "wb") as f:
f.write(response.content)
Lihtne ja läbipaistev hinnakujundus
Alusta tasuta, skaleeri kasvades.
Vaba
50 krediiti
- Kokoro, Piper, VITS, MeloTTS
- 500 tähemärgi piirang
- 3 g/h (kontot ei ole)
Starter
500 krediiti kuus
- Kõik 22+ mudelit
- 5000 tähemärgi piir
- Hääle kloonimine
Pro
2000 krediiti kuus
- Kõik Starter'is
- API-juurdepääs
- Prioriteetne töötlemine
Ettevõtlus
10 000 krediiti kuus
- Kõik on Pro's
- Pulk API
- Prioriteetne järjekord
Korduma kippuvad küsimused
Alusta AI-hääle kasutamist tänapäeval
Liitu loojate, arendajate ja ettevõtetega, kes kasutavad TTS.ai