# Ready to Speak: Aligning LLMs for TTS-Friendly Text Generation

arXiv: https://arxiv.org/abs/2609.01246 · HTML: https://mlsanity.com/paper/2609.01246/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Preference alignment for recommenders and RAG, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 20 of its 36 references that are in the map.
- First posted on arXiv 1 Sep 2026.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Preference alignment for recommenders and RAG](https://mlsanity.com/alignment/preference-alignment-for-recommenders-and-rag/)

## Builds on (most cited first, 20 of 20)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [LIMA: Less Is More for Alignment](https://mlsanity.com/paper/2305.11206/) (2023)
- [Prometheus: Inducing Fine-grained Evaluation Capability in Language Models](https://mlsanity.com/paper/2310.08491/) (2023)
- [Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models](https://mlsanity.com/paper/2405.01535/) (2024)
- [Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs](https://mlsanity.com/paper/2506.14245/) (2025)
- [Koel-TTS: Enhancing LLM based Speech Generation with Preference Alignment and Classifier Free Guidance](https://mlsanity.com/paper/2502.05236/) (2025)
- [Towards Controllable Speech Synthesis in the Era of Large Language Models: A Systematic Survey](https://mlsanity.com/paper/2412.06602/) (2024)
- [Preference Alignment Improves Language Model-Based TTS](https://mlsanity.com/paper/2409.12403/) (2024)
- [Advancing Zero-shot Text-to-Speech Intelligibility across Diverse Domains via Preference Alignment](https://mlsanity.com/paper/2505.04113/) (2025)
- [Constrained Discrete Diffusion](https://mlsanity.com/paper/2503.09790/) (2025)
- [Shot-by-Shot: Film-Grammar-Aware Training-Free Audio Description Generation](https://mlsanity.com/paper/2504.01020/) (2025)
- [A Chat About Boring Problems: Studying GPT-based text normalization](https://mlsanity.com/paper/2309.13426/) (2023)
- [ELITR-Bench: A Meeting Assistant Benchmark for Long-Context Language Models](https://mlsanity.com/paper/2403.20262/) (2024)
- [Speechworthy Instruction-tuned Language Models](https://mlsanity.com/paper/2409.14672/) (2024)
- [FaST: Feature-aware Sampling and Tuning for Personalized Preference Alignment with Limited Data](https://mlsanity.com/paper/2508.04698/) (2025)
- [CLID: Controlled-Length Image Descriptions with Limited Data](https://mlsanity.com/paper/2211.14835/) (2022)
- [PolyNorm: Few-Shot LLM-Based Text Normalization for Text-to-Speech](https://mlsanity.com/paper/2511.03080/) (2025)
- [Beyond One-Size-Fits-All Summarization: Customizing Summaries for Diverse Users](https://mlsanity.com/paper/2503.10675/) (2025)
- [CIE: Controlling Language Model Text Generations Using Continuous Signals](https://mlsanity.com/paper/2505.13448/) (2025)

## Abstract (arXiv)

Current Large Language Models (LLMs) are primarily optimized for written text, often producing outputs that are grammatically correct and helpful yet poorly suited for spoken delivery via Text-to-Speech (TTS). In this work, we study how to make LLMs natively generate TTS-friendly text, which we frame as a preference alignment problem: instead of relying on downstream rewriting modules, we directly align LLMs to generate text optimized for spoken delivery. We introduce two preference datasets spanning different target domains, CORA and Recipe, which contain paired TTS-friendly and TTS-unfriendly responses. We further propose an evaluation suite combining a pattern-based heuristic metric, a TTS→ASR evaluation pipeline, and a MUSHRA listening study with human judges. Our experiments compare the recently proposed Feature-aware Sampling and Tuning (FaST) framework -- leveraging interpretable features instead of a black-box reward model -- against an array of alignment baselines on the TTS-friendly generation task. Notably, we found that FaST achieves the best overall tradeoff between TTS-friendliness and helpfulness across various settings. We also identified a strong correlation between our different metrics, highlighting the ability to reliably assess TTS-friendliness via an efficient heuristic.