# BASE TTS: Lessons from building a billion-parameter Text-to-Speech model on 100K hours of data

arXiv: https://arxiv.org/abs/2402.08093 · HTML: https://mlsanity.com/paper/2402.08093/

## Key facts

- Cited by 75 papers in the map (data through 14 Oct 2026).
- Builds on 72 of its 105 references that are in the map.
- First posted on arXiv 12 Feb 2024.

## Builds on (most cited first, 30 of 72)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation](https://mlsanity.com/paper/2206.10789/) (2022)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions](https://mlsanity.com/paper/1712.05884/) (2017)
- [SoundStream: An End-to-End Neural Audio Codec](https://mlsanity.com/paper/2107.03312/) (2021)
- [Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2301.02111/) (2023)
- [FastSpeech 2: Fast and High-Quality End-to-End Text to Speech](https://mlsanity.com/paper/2006.04558/) (2020)
- [High Fidelity Neural Audio Compression](https://mlsanity.com/paper/2210.13438/) (2022)
- [AudioLM: a Language Modeling Approach to Audio Generation](https://mlsanity.com/paper/2209.03143/) (2022)
- [Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech](https://mlsanity.com/paper/2106.06103/) (2021)
- [Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech](https://mlsanity.com/paper/2105.06337/) (2021)

## Built on by (most cited first, 30 of 75)

- [CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens](https://mlsanity.com/paper/2407.05407/) (2024)
- [CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models](https://mlsanity.com/paper/2412.10117/) (2024)
- [MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer](https://mlsanity.com/paper/2409.00750/) (2024)
- [VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2406.05370/) (2024)
- [Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis](https://mlsanity.com/paper/2502.04128/) (2025)
- [SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Words](https://mlsanity.com/paper/2406.13340/) (2024)
- [Autoregressive Speech Synthesis without Vector Quantization](https://mlsanity.com/paper/2407.08551/) (2024)
- [Language Model Can Listen While Speaking](https://mlsanity.com/paper/2408.02622/) (2024)
- [Recent Advances in Discrete Speech Tokens: A Review](https://mlsanity.com/paper/2502.06490/) (2025)
- [Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey](https://mlsanity.com/paper/2412.18619/) (2024)
- [F5R-TTS: Improving Flow-Matching based Text-to-Speech with Group Relative Policy Optimization](https://mlsanity.com/paper/2504.02407/) (2025)
- [EmergentTTS-Eval: Evaluating TTS Models on Complex Prosodic, Expressiveness, and Linguistic Challenges Using Model-as-a-Judge](https://mlsanity.com/paper/2505.23009/) (2025)
- [Enhancing Zero-shot Text-to-Speech Synthesis with Human Feedback](https://mlsanity.com/paper/2406.00654/) (2024)
- [Emilia: A Large-Scale, Extensive, Multilingual, and Diverse Dataset for Speech Generation](https://mlsanity.com/paper/2501.15907/) (2025)
- [FocalCodec: Low-Bitrate Speech Coding via Focal Modulation Networks](https://mlsanity.com/paper/2502.04465/) (2025)
- [MoonCast: High-Quality Zero-Shot Podcast Generation](https://mlsanity.com/paper/2503.14345/) (2025)
- [Fast and High-Quality Auto-Regressive Speech Synthesis via Speculative Decoding](https://mlsanity.com/paper/2410.21951/) (2024)
- [IndicVoices-R: Unlocking a Massive Multilingual Multi-speaker Speech Corpus for Scaling Indian TTS](https://mlsanity.com/paper/2409.05356/) (2024)
- [CoVoMix: Advancing Zero-Shot Speech Generation for Human-like Multi-talker Conversations](https://mlsanity.com/paper/2404.06690/) (2024)
- [EmoKnob: Enhance Voice Cloning with Fine-Grained Emotion Control](https://mlsanity.com/paper/2410.00316/) (2024)
- [Enhancing Low-Resource ASR through Versatile TTS: Bridging the Data Gap](https://mlsanity.com/paper/2410.16726/) (2024)
- [Robust Zero-Shot Text-to-Speech Synthesis with Reverse Inference Optimization](https://mlsanity.com/paper/2407.02243/) (2024)
- [CoVoMix2: Advancing Zero-Shot Dialogue Generation with Fully Non-Autoregressive Flow Matching](https://mlsanity.com/paper/2506.00885/) (2025)
- [Accelerating Codec-based Speech Synthesis with Multi-Token Prediction and Speculative Decoding](https://mlsanity.com/paper/2410.13839/) (2024)
- [Pseudo-Autoregressive Neural Codec Language Models for Efficient Zero-Shot Text-to-Speech Synthesis](https://mlsanity.com/paper/2504.10352/) (2025)
- [Bayesian Parameter-Efficient Fine-Tuning for Overcoming Catastrophic Forgetting](https://mlsanity.com/paper/2402.12220/) (2024)
- [When Large Language Models Meet Speech: A Survey on Integration Approaches](https://mlsanity.com/paper/2502.19548/) (2025)
- [Emotional Dimension Control in Language Model-Based Text-to-Speech: Spanning a Broad Spectrum of Human Emotions](https://mlsanity.com/paper/2409.16681/) (2024)
- [Takin: A Cohort of Superior Quality Zero-shot Speech Generation Models](https://mlsanity.com/paper/2409.12139/) (2024)
- [Rethinking MUSHRA: Addressing Modern Challenges in Text-to-Speech Evaluation](https://mlsanity.com/paper/2411.12719/) (2024)

## Abstract (arXiv)

We introduce a text-to-speech (TTS) model called BASE TTS, which stands for Big Adaptive Streamable TTS with Emergent abilities. BASE TTS is the largest TTS model to-date, trained on 100K hours of public domain speech data, achieving a new state-of-the-art in speech naturalness. It deploys a 1-billion-parameter autoregressive Transformer that converts raw texts into discrete codes ("speechcodes") followed by a convolution-based decoder which converts these speechcodes into waveforms in an incremental, streamable manner. Further, our speechcodes are built using a novel speech tokenization technique that features speaker ID disentanglement and compression with byte-pair encoding. Echoing the widely-reported "emergent abilities" of large language models when trained on increasing volume of data, we show that BASE TTS variants built with 10K+ hours and 500M+ parameters begin to demonstrate natural prosody on textually complex sentences. We design and share a specialized dataset to measure these emergent abilities for text-to-speech. We showcase state-of-the-art naturalness of BASE TTS by evaluating against baselines that include publicly available large-scale text-to-speech systems: YourTTS, Bark and TortoiseTTS. Audio samples generated by the model can be heard at https://amazon-ltts-paper.com/.