QPrintPreviewDialog @ action
22+ open-source models, 100+ voices, 32+ Ba a buƙata wani asusu ba.
KCharselect unicode block name
26 kayan aiki powered by 24+ open-source AI models
QFontDatabase
Samfurin da ya fi faɗi na sifofin TTS masu ma'ana-farare a cikin dandamali guda
Tortoise TTS
StyleTTS 2
OpenVoice
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.
Mafi kyau ga: High-quality TTS with minimal latency, streaming applications
QShortcut
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.
Mafi kyau ga: Quick previews, accessibility, and embedded applications
QShortcut
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.
Mafi kyau ga: General-purpose text-to-speech with natural prosody
QShortcut
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.
Mafi kyau ga: Shiryoyin ayuka na samarwa suna buƙatar TTS mai sauri, da ya ƙunshi yarukan da dama
QShortcut
Bark Standard
Transformer-based text-to-audio model that generates realistic speech, music, and sound effects.
Mawallafi: Suno · Lasisi: MIT
@ action
Bark Small Standard
Lighter version of Bark with faster inference and lower memory usage.
Mawallafi: Suno · Lasisi: MIT
@ action
CosyVoice 2 Standard
Alibaba's scalable streaming TTS with human-parity naturalness and near-zero latency.
Mawallafi: Alibaba (Tongyi Lab) · Lasisi: Apache 2.0
@ action
Dia TTS Standard
Tsarin samar da tattaunawar masu magana da yawa wanda ke samar da tattaunawar halitta tsakanin masu magana.
Mawallafi: Nari Labs · Lasisi: Apache 2.0
@ action
Parler TTS Standard
Describe the voice you want in natural language and Parler generates matching speech.
Mawallafi: Hugging Face · Lasisi: Apache 2.0
@ action
IndexTTS-2 Standard
Zero-shot TTS with fine-grained emotion control and high expressiveness.
Mawallafi: Index Team · Lasisi: Apache 2.0
@ action
Spark TTS Standard
Voice cloning TTS with controllable emotion and speaking style via prompts.
Mawallafi: SparkAudio · Lasisi: Apache 2.0
@ action
GPT-SoVITS Standard
Few-shot voice cloning TTS that replicates any voice from just 5 seconds of audio.
Mawallafi: RVC-Boss · Lasisi: MIT
@ action
Orpheus Standard
Human-level emotional TTS model trained on 100K hours of speech data.
Mawallafi: Canopy Labs · Lasisi: Llama 3.2 Community
@ action
Qwen3 TTS Standard
Alibaba's multilingual TTS with voice cloning, preset voices, and voice design from text.
Mawallafi: Alibaba (Qwen) · Lasisi: Apache 2.0
@ actionCosyVoice 2
Alibaba's scalable streaming TTS with human-parity naturalness and near-zero latency.
Yare: en, zh, ja, ko, fr, de, it, es
QShortcutIndexTTS-2
Zero-shot TTS with fine-grained emotion control and high expressiveness.
Yare: en, zh
QShortcutSpark TTS
Voice cloning TTS with controllable emotion and speaking style via prompts.
Yare: en, zh
QShortcutGPT-SoVITS
Few-shot voice cloning TTS that replicates any voice from just 5 seconds of audio.
Yare: en, zh, ja, ko
QShortcut
Chatterbox
State-of-the-art zero-shot voice cloning with emotion control from Resemble AI.
Yare: en
QShortcutQwen3 TTS
Alibaba's multilingual TTS with voice cloning, preset voices, and voice design from text.
Yare: en, zh, ja, ko, de, fr, ru, pt, es, it
QShortcutDeveloper-First API
OpenAI-compatible REST API. One endpoint, 22+ models. Streaming support for real-time applications.
- QPrintPreviewDialog
- Streaming TTS ga shiryoyin ayuka na lokaci na gaskiya
- Preview-size
- QDialogButtonBox
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)QPrintPreviewDialog
Ka fara kyauta. Ka girma kamar yadda kake girma.
QDialogButtonBox
credits
- Kokoro, Piper, VITS, MeloTTS
- 500 haske
- 3 gen/hour (no account)
QShortcut
2000 credits/month
- Duk abin da ke cikin Mai Farawa
- Aika API
- QDialogButtonBox
Tambayar da ake yi da yawa
KCharselect unicode block name
Haɗu da masu ƙirƙira, masu haɓakawa, da kasuwancin da ke amfani da TTS.ai