# Real-Time Text-to-Speech Model
**URL:**
**Author:**  [@Muhammad-Faizan-Ahme](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FMuhammad-Faizan-Ahme)%5C
**Post date:** [January 4, 2025, 5:32pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Freal-time-text-to-speech-model%2F134253%2F1 "2025-01-04T17:32:59Z")
Greetings everyone, I’m currently looking for real-time tts model that can create an audio as soon as I type. Kindly guide me in this regard.
---
**Author:**  [@Alanturner2](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FAlanturner2)%5C
**Post date:** [January 5, 2025, 9:31am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Freal-time-text-to-speech-model%2F134253%2F2 "2025-01-05T09:31:08Z")
Greetings! If you’re looking for a real-time text-to-speech (TTS) model that generates audio immediately as you type, here are some excellent options:
### Open-Source Models
1. **Mozilla TTS:**
2. **Coqui TTS:**
3. **FastSpeech 2 + HiFi-GAN:**
### Pre-Trained APIs
1. **Google Cloud Text-to-Speech API:**
2. **Microsoft Azure Speech Service:**
3. **AWS Polly:**
### Specialized Real-Time Models
1. **ElevenLabs (Proprietary):**
2. **Riffusion:**
#### Setup and Latency Considerations
- For open-source solutions, ensure you’re using a GPU for low latency.
- Real-time TTS involves a balance between audio quality and inference speed. Look into frameworks like ONNX Runtime or TensorRT for optimizing model performance.
Feel free to share your use case for tailored recommendations!
---
**Author:**  [@Muhammad-Faizan-Ahme](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FMuhammad-Faizan-Ahme)%5C
**Post date:** [January 5, 2025, 11:26am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Freal-time-text-to-speech-model%2F134253%2F3 "2025-01-05T11:26:21Z")
Thank You for guidance.