task · first seen 4 Oct 2026
text-to-speech
Also: TTS, speech synthesis, expressive speech synthesis
Generating spoken audio from written text using neural models.
Text-to-speech is the long-standing task of converting written text into spoken audio, now dominated by neural approaches. The sources show ordinary activity across the field, with no single new idea driving it: an interpretability paper tracing emotion-control circuits in LLM-based TTS, a Yorùbá text corpus release, Turkish models distilled from VoxCPM teachers, a study of classifier-free guidance hurting speaker similarity in few-step flow-matching decoders, and Lombard-effect adaptation. On the code side there are on-device Core ML runtimes, tiny ONNX models, inclusionAI's Ming-3.0-tts MoE family, and Claude Code skills that use TTS or voice cloning as a component.
The field is mature, so the mention spike reflects broad background volume rather than a new technique. The narrower threads may be worth tracking separately: tiny models distilled entirely on synthetic speech, few-step flow-matching decoders, and LLM-based TTS with natural-language voice control.
Analyst note (established), 17 Nov 2026.
Mentions per week
PapersCodeDiscussion
Rank 79 on 14 Nov 2026 · 48 mentions in 28 days · 45 independent groups · papers → code → discussion · first seen 6 weeks ago · acceleration -0.29
Earliest sources
- Tracing a Sparse Emotion-Control Circuit in LLM-Based Text-to-SpeechPapers · 4 Oct 2026 · Hongfei Du, Jiacheng Shi, Yanfu Zhang, Ye Gao
- The ÌròyìnSpeech Text Corpus: 24,905 Curated Yorùbá Sentences for Speech and Language TechnologyPapers · 4 Oct 2026 · Kola Tubosun, Anuoluwapo Aremu, Tolulope Ogunremi, Iroro Orife, David Ifeoluwa A…
- Corvelis/irodori-tts-coremlCode · 4 Oct 2026 · Corvelis · 40 stars
- ninja8170/VoxAsterCode · 4 Oct 2026 · ninja8170 · 26 stars
- A Comprehensive Objective Evaluation of Modern Text-to-Speech for Turkish Using Speech Quality Assessment ModelsPapers · 5 Oct 2026 · Yunus Emre Ozkose, Alperen Kahraman, Ali Haznedaroglu
- Paradee: Distilling Kokoro-82M into an 8M-Parameter Single-Voice Text-to-Speech ModelPapers · 5 Oct 2026 · Sahil Mahendrakar
Latest sources
- carlosamus123/HA-MessengerCode · 16 Nov 2026 · carlosamus123 · 10 stars
- n4ze3m/tiny-vocaCode · 14 Nov 2026 · n4ze3m · 666 stars
- Auditory-Feedback-Conditioned Flow TTS for Implicit Lombard AdaptationPapers · 14 Nov 2026 · Yunya Wang, Satoshi Nakamura
- syydaniel/kaikouCode · 11 Nov 2026 · syydaniel · 47 stars
- Human-Likeness and Conversational Preference Diverge for Synthesized Agent Speech in Customer-Service CallsPapers · 11 Nov 2026 · Jeffrey M. Girard, Antony D'Avirro, Jason Z. Zheng, Jacqueline R. Vertino, Benja…
- Alania-2: Turkish text-to-speech with instant and fine-tuned voice cloningPapers · 10 Nov 2026 · Sezgin Saygili, Emre Kaplaner, Oncel Ozgul, Fikri San Koktas
- Antalia-2 Mini: A 7.6-million-parameter Turkish text-to-speech model trained entirely on synthetic speechPapers · 10 Nov 2026 · Sezgin Saygili, Emre Kaplaner, Oncel Ozgul, Fikri San Koktas
- Guidance at Pure Noise Erodes Speaker Similarity in Few-Step Token-Conditioned Flow-Matching TTSPapers · 8 Nov 2026 · Jaeho Lee, Han-Lim Choi
- podcatcher962/moyin-readerCode · 7 Nov 2026 · podcatcher962 · 17 stars
- jastfan/explainroo-uiCode · 7 Nov 2026 · jastfan · 40 stars
- achun1107/video-kitCode · 7 Nov 2026 · achun1107 · 103 stars
- syydaniel/kaziCode · 6 Nov 2026 · syydaniel · 30 stars