20+ open-source models, 107+ voices, 32+ languages. No account required.
Everything You Need for Voice AI
30+ tools powered by open-source AI models
20+ AI Voice Models
The most comprehensive collection of open-source TTS models in one platform
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.
Best for: High-quality TTS with minimal latency, streaming applications
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.
Best for: Quick previews, accessibility, and embedded applications
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.
Best for: General-purpose text-to-speech with natural prosody
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.
Best for: Production applications needing fast, multilingual TTS
Bark Standard
Transformer-based text-to-audio model that generates realistic speech, music, and sound effects.
Developer: Suno · License: MIT
Bark Small Standard
Lighter version of Bark with faster inference and lower memory usage.
Developer: Suno · License: MIT
CosyVoice 2 Standard
Alibaba's scalable streaming TTS with human-parity naturalness and near-zero latency.
Developer: Alibaba (Tongyi Lab) · License: Apache 2.0
Dia TTS Standard
Multi-speaker dialog generation model that creates natural conversations between speakers.
Developer: Nari Labs · License: Apache 2.0
Parler TTS Standard
Describe the voice you want in natural language and Parler generates matching speech.
Developer: Hugging Face · License: Apache 2.0
GLM-TTS Standard
Achieves the lowest character error rate among open-source TTS models.
Developer: Zhipu AI · License: GLM-4 License
IndexTTS-2 Standard
Zero-shot TTS with fine-grained emotion control and high expressiveness.
Developer: Index Team · License: Bilibili Model License
Spark TTS Standard
Voice cloning TTS with controllable emotion and speaking style via prompts.
Developer: SparkAudio · License: CC BY-NC-SA 4.0
GPT-SoVITS Standard
Few-shot voice cloning TTS that replicates any voice from just 5 seconds of audio.
Developer: RVC-Boss · License: MIT
Orpheus Standard
Human-level emotional TTS model trained on 100K hours of speech data.
Developer: Canopy Labs · License: Llama 3.2 Community
Qwen3 TTS Standard
Alibaba's multilingual TTS with voice cloning, preset voices, and voice design from text.
Developer: Alibaba (Qwen) · License: Apache 2.0
Chatterbox Premium
State-of-the-art zero-shot voice cloning with emotion control from Resemble AI.
Quality:
Tortoise TTS Premium
Multi-voice text-to-speech focused on quality with autoregressive architecture.
Quality:
StyleTTS 2 Premium
Human-level text-to-speech through style diffusion and adversarial training.
Quality:
OpenVoice Premium
Instant voice cloning with granular control over style, emotion, and accent.
Quality:
Sesame CSM Premium
Conversational speech model generating natural dialogue with appropriate timing and emotion.
Quality:
CosyVoice 2
Alibaba's scalable streaming TTS with human-parity naturalness and near-zero latency.
Languages: en, zh, ja, ko, fr, de, it, es
GLM-TTS
Achieves the lowest character error rate among open-source TTS models.
Languages: en, zh
IndexTTS-2
Zero-shot TTS with fine-grained emotion control and high expressiveness.
Languages: en, zh
Spark TTS
Voice cloning TTS with controllable emotion and speaking style via prompts.
Languages: en, zh
GPT-SoVITS
Few-shot voice cloning TTS that replicates any voice from just 5 seconds of audio.
Languages: en, zh, ja, ko
Chatterbox
State-of-the-art zero-shot voice cloning with emotion control from Resemble AI.
Languages: en
Tortoise TTS
Multi-voice text-to-speech focused on quality with autoregressive architecture.
Languages: en
OpenVoice
Instant voice cloning with granular control over style, emotion, and accent.
Languages: en, zh, ja, ko, fr, de, es, it
Qwen3 TTS
Alibaba's multilingual TTS with voice cloning, preset voices, and voice design from text.
Languages: en, zh, ja, ko, de, fr, ru, pt, es, it
Developer-First API
OpenAI-compatible REST API. One endpoint, 22+ models. Streaming support for real-time applications.
- OpenAI-compatible format
- Streaming TTS for real-time apps
- Batch processing for large jobs
- Webhook notifications
pip install ttsai
npm install @ttsainpm/ttsai
from tts_ai import TTSClient
client = TTSClient(api_key="sk-tts-xxx")
audio = client.generate(
text="Hello from TTS.ai!",
model="kokoro",
voice="af_bella",
)
client.save(audio, "output.mp3")Simple, Transparent Pricing
Start free. Scale as you grow.
Free
$0
15,000 characters
- Kokoro, Piper, VITS, MeloTTS
- 500 character limit
- 3 gen/hour (no account)
Starter
$9/mo
500,000 characters/month
- All 22+ models
- 100,000 chars per generation
- Voice Cloning
Most Popular
Pro
$29/mo
2,000,000 characters/month
- Everything in Starter
- API access
- Priority processing
Frequently Asked Questions
TTS.ai is the most comprehensive AI voice platform, offering 22+ text-to-speech models, voice cloning, speech-to-text, and audio tools. All models are open source with no vendor lock-in.
Yes! TTS.ai offers free text-to-speech with Kokoro, Piper, VITS, and MeloTTS models. No account required. Sign up to get 15,000 free characters and access all models. Paid plans start at $9/month.
For speed, use Kokoro or Piper. For quality, try CosyVoice 2 or StyleTTS 2. For voice cloning, use Chatterbox or GPT-SoVITS. For dialog, use Dia TTS. Try multiple models on the same text to compare.
Yes. OpenAI-compatible REST API for TTS, STT, voice cloning, and audio tools. Available on Pro ($29/mo) and Enterprise ($99/mo) plans. View documentation at tts.ai/api/.
Voice quality varies by model. Premium models like CosyVoice 2, StyleTTS 2, and Chatterbox produce near-human quality speech with natural intonation and emotion. Free models like Kokoro offer excellent quality for most use cases.
TTS.ai supports 30+ languages across its model library. English has the widest model support, but models like CosyVoice 2 cover Chinese, Japanese, and Korean; GPT-SoVITS handles Chinese, Japanese, Korean, and English; and MeloTTS supports English, Spanish, French, Chinese, Japanese, and Korean.
Yes. All processing happens on our dedicated GPU servers. We do not store your text input or generated audio after delivery. Uploaded voice samples for cloning are used only for the current session and are not retained. We never share your data with third parties or use it to train models.
Yes. All audio generated on TTS.ai is yours to use commercially, including for YouTube videos, podcasts, audiobooks, apps, advertisements, and products. Our models are open source under permissive licenses (MIT, Apache 2.0). No royalties or attribution required.
TTS.ai generates audio in WAV format by default for maximum quality. You can convert to MP3, FLAC, OGG, or M4A using our free Audio Converter tool. The API supports specifying your preferred output format directly in the request.
Upload a short audio sample (as little as 5 seconds) of the voice you want to clone, then type any text to generate speech in that voice. Models like Chatterbox, GPT-SoVITS, and CosyVoice 2 support voice cloning. The cloned voice captures tone, accent, and speaking style.
Free models (Kokoro, Piper, VITS, MeloTTS) require no account and cost zero characters. Standard models (2,000 characters/1K input) include Bark, CosyVoice 2, F5-TTS, and Dia. Premium models (4,000 characters/1K input) include OpenVoice, Chatterbox, StyleTTS 2, and Tortoise. Paid models generally offer higher quality, more voices, and additional features like voice cloning.
Yes. The API supports batch processing for converting large volumes of text to speech. Submit multiple requests and retrieve results asynchronously using job UUIDs. Enterprise plans ($99/mo) include priority queue access for faster batch processing. Ideal for audiobook production, course content, and large-scale voiceover projects.
Start Using AI Voice Today
Join creators, developers, and businesses using TTS.ai