Prosti AI Besedilo v govor
22+ modeli odprtega vira, 100+ glasov, 32+ jeziki. Račun ni potreben.
Vse, kar potrebuješ za glasovno inteligenco
26 orodij, ki jih poganjajo 24+ modeli AI z odprtim virom
22+ AI Glasovni modeli
Najobsežnejša zbirka modelov TTS na odprtem viru v eni platformi
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.
Najboljše za: High-quality TTS with minimal latency, streaming applications
Poskusite svobodnoPiper 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.
Najboljše za: Quick previews, accessibility, and embedded applications
Poskusite svobodnoVITS 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.
Najboljše za: General-purpose text-to-speech with natural prosody
Poskusite svobodnoMeloTTS 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.
Najboljše za: Zahtevki za proizvodnjo, ki potrebujejo hitro, večjezično TTS
Poskusite svobodnoBark Standard
Transformer-based text-to-audio model that generates realistic speech, music, and sound effects.
Razvijalec: Suno · Licenca: MIT
Poskusi.Bark Small Standard
Lighter version of Bark with faster inference and lower memory usage.
Razvijalec: Suno · Licenca: MIT
Poskusi.CosyVoice 2 Standard
Alibaba's scalable streaming TTS with human-parity naturalness and near-zero latency.
Razvijalec: Alibaba (Tongyi Lab) · Licenca: Apache 2.0
Poskusi.Dia TTS Standard
Večzvočniški dialogski model, ki ustvarja naravne pogovore med zvočniki.
Razvijalec: Nari Labs · Licenca: Apache 2.0
Poskusi.Parler TTS Standard
Describe the voice you want in natural language and Parler generates matching speech.
Razvijalec: Hugging Face · Licenca: Apache 2.0
Poskusi.IndexTTS-2 Standard
Zero-shot TTS with fine-grained emotion control and high expressiveness.
Razvijalec: Index Team · Licenca: Apache 2.0
Poskusi.Spark TTS Standard
Voice cloning TTS with controllable emotion and speaking style via prompts.
Razvijalec: SparkAudio · Licenca: Apache 2.0
Poskusi.GPT-SoVITS Standard
Few-shot voice cloning TTS that replicates any voice from just 5 seconds of audio.
Razvijalec: RVC-Boss · Licenca: MIT
Poskusi.Orpheus Standard
Human-level emotional TTS model trained on 100K hours of speech data.
Razvijalec: Canopy Labs · Licenca: Llama 3.2 Community
Poskusi.Qwen3 TTS Standard
Alibaba's multilingual TTS with voice cloning, preset voices, and voice design from text.
Razvijalec: Alibaba (Qwen) · Licenca: Apache 2.0
Poskusi.CosyVoice 2
Alibaba's scalable streaming TTS with human-parity naturalness and near-zero latency.
Jeziki: en, zh, ja, ko, fr, de, it, es
Klonov glasIndexTTS-2
Zero-shot TTS with fine-grained emotion control and high expressiveness.
Jeziki: en, zh
Klonov glasSpark TTS
Voice cloning TTS with controllable emotion and speaking style via prompts.
Jeziki: en, zh
Klonov glasGPT-SoVITS
Few-shot voice cloning TTS that replicates any voice from just 5 seconds of audio.
Jeziki: en, zh, ja, ko
Klonov glasChatterbox
Najmodernejši kloniranje glasu z obvladovanjem čustev iz Resemble AI.
Jeziki: en
Klonov glasTortoise TTS
Večglasno besedilo-to-speech osredotočen na kakovost z avtoregresivno arhitekturo.
Jeziki: en
Klonov glasOpenVoice
Instant voice cloning with granular control over style, emotion, and accent.
Jeziki: en, zh, ja, ko, fr, de, es, it
Klonov glasQwen3 TTS
Alibaba's multilingual TTS with voice cloning, preset voices, and voice design from text.
Jeziki: en, zh, ja, ko, de, fr, ru, pt, es, it
Klonov glasRazvijalec-prva API
Združljiv z OpenAI REST API. En opazovani dogodek, 22+ modeli. Pogon podpore za aplikacije v realnem času.
- Združljiva z OpenAI formatom
- Streaming TTS za aplikacije v realnem času
- Serija obdelave za velika delovna mesta
- Spletna obvestila
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)Preprosta, pregledna cena
Začnite svobodno.
Prosto
50 kreditov
- Kokoro, Piper, VITS, MeloTTS
- Omejitev 500 znakov
- 3 gen/ur (brez računa)
Prof.
2.000 kreditov mesečno
- Vse v zagonu
- Dostop API
- Prednostna obdelava
Pogosta vprašanja
Začnite uporabljati AI glas danes
Pridružite se ustvarjalcem, razvijalcem in podjetjem, ki uporabljajo TTS.ai