Free AI Tekst-u-govor
22+ modela otvorenog koda, 100+ glasova, 32+ Nije potreban račun.
Sve što trebate za Voice AI
26 alata podržanih od strane 24+ modela AI otvorenog koda
22+ AI glasovnih modela
Najopsežnija kolekcija TTS modela otvorenog koda na jednoj 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.
Najbolje za: High-quality TTS with minimal latency, streaming applications
Probaj besplatnoPiper 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.
Najbolje za: Quick previews, accessibility, and embedded applications
Probaj besplatnoVITS 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.
Najbolje za: General-purpose text-to-speech with natural prosody
Probaj besplatnoMeloTTS 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.
Najbolje za: Produkcijske aplikacije trebaju brz, višejezični TTS
Probaj besplatnoBark Standard
Transformer-based text-to-audio model that generates realistic speech, music, and sound effects.
Programer: Suno · Licenca: MIT
Probaj.Bark Small Standard
Lighter version of Bark with faster inference and lower memory usage.
Programer: Suno · Licenca: MIT
Probaj.CosyVoice 2 Standard
Alibaba's scalable streaming TTS with human-parity naturalness and near-zero latency.
Programer: Alibaba (Tongyi Lab) · Licenca: Apache 2.0
Probaj.Dia TTS Standard
Multi-speaker dialogue generation model that creates natural conversations between speakers.
Programer: Nari Labs · Licenca: Apache 2.0
Probaj.Parler TTS Standard
Describe the voice you want in natural language and Parler generates matching speech.
Programer: Hugging Face · Licenca: Apache 2.0
Probaj.IndexTTS-2 Standard
Zero-shot TTS with fine-grained emotion control and high expressiveness.
Programer: Index Team · Licenca: Apache 2.0
Probaj.Spark TTS Standard
Voice cloning TTS with controllable emotion and speaking style via prompts.
Programer: SparkAudio · Licenca: Apache 2.0
Probaj.GPT-SoVITS Standard
Few-shot voice cloning TTS that replicates any voice from just 5 seconds of audio.
Programer: RVC-Boss · Licenca: MIT
Probaj.Orpheus Standard
Human-level emotional TTS model trained on 100K hours of speech data.
Programer: Canopy Labs · Licenca: Llama 3.2 Community
Probaj.Qwen3 TTS Standard
Alibaba's multilingual TTS with voice cloning, preset voices, and voice design from text.
Programer: Alibaba (Qwen) · Licenca: Apache 2.0
Probaj.CosyVoice 2
Alibaba's scalable streaming TTS with human-parity naturalness and near-zero latency.
Jezici: en, zh, ja, ko, fr, de, it, es
Clone VoiceIndexTTS-2
Zero-shot TTS with fine-grained emotion control and high expressiveness.
Jezici: en, zh
Clone VoiceSpark TTS
Voice cloning TTS with controllable emotion and speaking style via prompts.
Jezici: en, zh
Clone VoiceGPT-SoVITS
Few-shot voice cloning TTS that replicates any voice from just 5 seconds of audio.
Jezici: en, zh, ja, ko
Clone VoiceChatterbox
Najmodernije kloniranje glasa sa kontrolom emocija od Resemble AI.
Jezici: en
Clone VoiceTortoise TTS
Višeglasni tekst-u-govor fokusiran je na kvalitet sa autoregresivnom arhitekturom.
Jezici: en
Clone VoiceOpenVoice
Instant kloniranje glasa sa granularnom kontrolom nad stilom, emocijama i naglaskom.
Jezici: en, zh, ja, ko, fr, de, es, it
Clone VoiceQwen3 TTS
Alibaba's multilingual TTS with voice cloning, preset voices, and voice design from text.
Jezici: en, zh, ja, ko, de, fr, ru, pt, es, it
Clone VoiceDeveloper-First API
OpenAI-kompatibilni REST API. Jedna krajnja tačka, 22+ modela. Podrška za streaming aplikacija u realnom vremenu.
- OpenAI-kompatibilni format
- Streaming TTS za aplikacije u stvarnom vremenu
- Serijska obrada za velike zadatke
- Webhook obavijesti
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)Jednostavno, transparentno određivanje cijena
Počnite besplatno, povećavajte kako rastete.
Slobodan
50 kredita
- Kokoro, Piper, VITS, MeloTTS
- Limit 500 znakova
- 3 gen/sat (bez računa)
Pro
2,000 kredita/mjesečno
- Sve u Starteru
- API pristup
- Prioritetna obrada
Često postavljana pitanja
Počnite koristiti AI Voice danas
Pridružite se kreatorima, programerima i poduzećima koji koriste TTS.ai