Özgür yapay zeka Metinden KonuşmayaName
22+ açık kaynaklı model, 100+ ses, 32+ Hiçbir hesap gerekmez.
Sesli yapay zeka için ihtiyacınız olan her şey
24+ açık kaynaklı yapay zeka modeli tarafından desteklenen 26 araç
22+ Yapay Zeka Ses Modelleri
Tek bir platformda açık kaynaklı TTS modellerinin en kapsamlı koleksiyonu
Chatterbox
Tortoise TTS
StyleTTS 2
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.
En İyi: High-quality TTS with minimal latency, streaming applications
Bedava Dene
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.
En İyi: Quick previews, accessibility, and embedded applications
Bedava Dene
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.
En İyi: General-purpose text-to-speech with natural prosody
Bedava Dene
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.
En İyi: Hızlı, çok dilli TTS gerektiren üretim uygulamaları
Bedava Dene
Bark Standard
Transformer-based text-to-audio model that generates realistic speech, music, and sound effects.
Geliştirici: Suno · Lisans: MIT
Dene.
Bark Small Standard
Lighter version of Bark with faster inference and lower memory usage.
Geliştirici: Suno · Lisans: MIT
Dene.
CosyVoice 2 Standard
Alibaba's scalable streaming TTS with human-parity naturalness and near-zero latency.
Geliştirici: Alibaba (Tongyi Lab) · Lisans: Apache 2.0
Dene.
Dia TTS Standard
Hoparlörler arasında doğal sohbetler yaratan çoklu hoparlörlü diyalog üretim modeli.
Geliştirici: Nari Labs · Lisans: Apache 2.0
Dene.
Parler TTS Standard
Describe the voice you want in natural language and Parler generates matching speech.
Geliştirici: Hugging Face · Lisans: Apache 2.0
Dene.
IndexTTS-2 Standard
Zero-shot TTS with fine-grained emotion control and high expressiveness.
Geliştirici: Index Team · Lisans: Apache 2.0
Dene.
Spark TTS Standard
Voice cloning TTS with controllable emotion and speaking style via prompts.
Geliştirici: SparkAudio · Lisans: Apache 2.0
Dene.
GPT-SoVITS Standard
Few-shot voice cloning TTS that replicates any voice from just 5 seconds of audio.
Geliştirici: RVC-Boss · Lisans: MIT
Dene.
Orpheus Standard
Human-level emotional TTS model trained on 100K hours of speech data.
Geliştirici: Canopy Labs · Lisans: Llama 3.2 Community
Dene.
Qwen3 TTS Standard
Alibaba's multilingual TTS with voice cloning, preset voices, and voice design from text.
Geliştirici: Alibaba (Qwen) · Lisans: Apache 2.0
Dene.CosyVoice 2
Alibaba's scalable streaming TTS with human-parity naturalness and near-zero latency.
Diller: en, zh, ja, ko, fr, de, it, es
Klon SesIndexTTS-2
Zero-shot TTS with fine-grained emotion control and high expressiveness.
Diller: en, zh
Klon SesSpark TTS
Voice cloning TTS with controllable emotion and speaking style via prompts.
Diller: en, zh
Klon SesGPT-SoVITS
Few-shot voice cloning TTS that replicates any voice from just 5 seconds of audio.
Diller: en, zh, ja, ko
Klon Ses
OpenVoice
Instant voice cloning with granular control over style, emotion, and accent.
Diller: en, zh, ja, ko, fr, de, es, it
Klon SesQwen3 TTS
Alibaba's multilingual TTS with voice cloning, preset voices, and voice design from text.
Diller: en, zh, ja, ko, de, fr, ru, pt, es, it
Klon SesGeliştirici Öncesi API
OpenAI uyumlu REST API. Tek son nokta, 22+ model. Gerçek zamanlı uygulamalar için akış desteği.
- OpenAI uyumlu biçim
- Gerçek zamanlı uygulamalar için TTS akışı
- Büyük işler için grup işlemi
- Webhook bildirimleri
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)Basit, şeffaf fiyatlandırma
Bedava başla, büyüdükçe ölçeklen.
Özgür
50 kredi
- Kokoro, Piper, VITS, MeloTTS
- 500 karakter sınırı
- 3 gen/saat (hesap yok)
Pro
2,000 kredi/ay
- Başlatıcıdaki her şey
- API erişimi
- Öncelik işlemi
Sıkça Sorulan Sorular
Yapay Zeka Sesini Bugün Kullanmaya Başlayın
TTS.ai kullanan yaratıcılara, geliştiricilere ve işletmelere katılın