IA livre Texto ao Discurso
22+ modelos de código aberto, 100+ vozes, 32+ Línguas. Não é necessária conta.
Tudo o que você precisa para a IA de voz
26 ferramentas alimentadas por 24+ modelos de IA de código aberto
22+ modelos de voz da IA
A coleção mais abrangente de modelos TTS de código aberto em uma plataforma
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.
Melhor para: High-quality TTS with minimal latency, streaming applications
Tente Gratuito
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.
Melhor para: Quick previews, accessibility, and embedded applications
Tente Gratuito
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.
Melhor para: General-purpose text-to-speech with natural prosody
Tente Gratuito
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.
Melhor para: Aplicações de produção que precisam de TTS rápido e multilingue
Tente Gratuito
Bark Standard
Transformer-based text-to-audio model that generates realistic speech, music, and sound effects.
Desenvolvedor: Suno · Licença: MIT
Experimenta-o.
Bark Small Standard
Lighter version of Bark with faster inference and lower memory usage.
Desenvolvedor: Suno · Licença: MIT
Experimenta-o.
CosyVoice 2 Standard
Alibaba's scalable streaming TTS with human-parity naturalness and near-zero latency.
Desenvolvedor: Alibaba (Tongyi Lab) · Licença: Apache 2.0
Experimenta-o.
Dia TTS Standard
Modelo de geração de diálogo multi-falantes que cria conversas naturais entre alto-falantes.
Desenvolvedor: Nari Labs · Licença: Apache 2.0
Experimenta-o.
Parler TTS Standard
Describe the voice you want in natural language and Parler generates matching speech.
Desenvolvedor: Hugging Face · Licença: Apache 2.0
Experimenta-o.
IndexTTS-2 Standard
Zero-shot TTS with fine-grained emotion control and high expressiveness.
Desenvolvedor: Index Team · Licença: Apache 2.0
Experimenta-o.
Spark TTS Standard
Voice cloning TTS with controllable emotion and speaking style via prompts.
Desenvolvedor: SparkAudio · Licença: Apache 2.0
Experimenta-o.
GPT-SoVITS Standard
Few-shot voice cloning TTS that replicates any voice from just 5 seconds of audio.
Desenvolvedor: RVC-Boss · Licença: MIT
Experimenta-o.
Orpheus Standard
Human-level emotional TTS model trained on 100K hours of speech data.
Desenvolvedor: Canopy Labs · Licença: Llama 3.2 Community
Experimenta-o.
Qwen3 TTS Standard
Alibaba's multilingual TTS with voice cloning, preset voices, and voice design from text.
Desenvolvedor: Alibaba (Qwen) · Licença: Apache 2.0
Experimenta-o.
CosyVoice 2
Alibaba's scalable streaming TTS with human-parity naturalness and near-zero latency.
Línguas: en, zh, ja, ko, fr, de, it, es
Clonar a Voz
IndexTTS-2
Zero-shot TTS with fine-grained emotion control and high expressiveness.
Línguas: en, zh
Clonar a Voz
Spark TTS
Voice cloning TTS with controllable emotion and speaking style via prompts.
Línguas: en, zh
Clonar a Voz
GPT-SoVITS
Few-shot voice cloning TTS that replicates any voice from just 5 seconds of audio.
Línguas: en, zh, ja, ko
Clonar a Voz
Chatterbox
Clonagem de voz de última geração com controle emotivo da IA Resemble.
Línguas: en
Clonar a Voz
Tortoise TTS
Texto para voz multi-voz focado na qualidade com arquitetura autorregressiva.
Línguas: en
Clonar a Voz
OpenVoice
Instant voice cloning with granular control over style, emotion, and accent.
Línguas: en, zh, ja, ko, fr, de, es, it
Clonar a Voz
Qwen3 TTS
Alibaba's multilingual TTS with voice cloning, preset voices, and voice design from text.
Línguas: en, zh, ja, ko, de, fr, ru, pt, es, it
Clonar a VozDesenvolvedor-Primeira API
API REST compatível com o OpenAI. Um endpoint, 22+ modelos. Suporte de transmissão para aplicações em tempo real.
- Formato compatível com OpenAI
- Streaming TTS para aplicativos em tempo real
- Processamento por lotes para grandes empregos
- Notificações de Webhook
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)
Preços simples, transparentes
Comece livre. Escala à medida que você cresce.
Grátis
50 créditos
- Kokoro, Piper, VITS, MeloTTS
- Limite de 500 caracteres
- 3 gen/hora (sem conta)
Início
500 créditos/mês
- Todos os modelos mais de 22
- Limite de 5.000 caracteres
- Clonagem de Voz
Pro
2 000 créditos/mês
- Tudo no Starter
- Acesso à API
- Tratamento prioritário
Perguntas Frequentes
Comece a usar a voz da IA hoje
Junte-se a criadores, desenvolvedores e empresas usando o TTS.ai