Series

TTS and Voice Cloning

Text-to-speech models, Chatterbox, voice cloning, prosody and the pronunciation problems of synthetic speech.

24 episodes
  1. 1

    Why Your TTS Sounds Great in English, Terrible Everywhere Else

    English AI voices are polished, but global languages hit a wall. Here's why text-to-speech breaks down for Hebrew, Hindi, and beyond.

    23:43 · 31 Mar 2026
  2. 2

    The TTS Developer's Dilemma: Size vs. Speed

    Stop guessing. We break down the critical trade-offs between model size, latency, and sample rate for production-ready voice apps.

    27:14 · 31 Mar 2026
  3. 3

    The Serverless Paradox: Why TTS Eats Your Budget

    How batch processing and smart queue management can slash TTS costs for episodic podcast production.

    21:22 · 18 Apr 2026
  4. 4

    Can AI Read the Room? TTS Prosody Explained

    Can TTS models truly infer emotion from text, or just mimic patterns? We break down the science of prosody.

    28:55 · 18 May 2026
  5. 5

    Why Your TTS Model Nails "Shabbat" but Not "Keren Hishtalmut

    Why multilingual TTS models handle loanwords but fail at niche vocabulary — and what you can do about it.

    27:25 · 22 May 2026
  6. 6

    How Chatterbox Locks Your Voice Clone Across Thousands of Generations

    Why most single-shot TTS models drift over time—and how Chatterbox's cached embedding approach solves it.

    28:02 · 23 May 2026
  7. 7

    Drawing the Melody: SSML's Hidden Power

    How SSML gives developers narrative control over AI voices — and why ElevenLabs became its center of gravity.

    28:30 · 1 Jun 2026
  8. 8

    Why Chatterbox Still Leads Open-Source TTS

    We break down the architecture of Chatterbox, the open-source TTS model powering this podcast, and why it remains state of the art.

    27:01 · 4 Aug 2026
  9. 9

    Why Resemble Gave Away Its Best Voice Model

    Resemble AI sells deepfake detection but open-sourced Chatterbox, a top TTS model. Here's the strategic logic.

    23:31 · 4 Aug 2026
  10. 10

    Why 30 Seconds of Audio Beats 3 Minutes for Voice Cloning

    Why adding more audio made Daniel's voice clones worse — and what it reveals about how voice embeddings actually work.

    23:08 · 9 Aug 2026
  11. 11

    How to Build Your Own TTS Audiobooks

    From M4B containers to chapter timing drift — the technical pipeline for creating audiobooks with synthetic voice.

    24:38 · 20 Aug 2026
  12. 12

    When Your TTS Model Eats the Numbers

    Numbers, dates, and acronyms break text-to-speech in specific, documented ways. Here's where normalization lives — and why it depends on your model.

    25:35 · 21 Sept 2026
  13. 13

    TTS Can't Pronounce Hebrew Inside English

    Your TTS reads Hebrew words with English phonetics. Here's why — and why the obvious fix doesn't work yet.

    21:13 · 22 Sept 2026
  14. 14

    When Your TTS Model Updates Itself

    Resemble pushed new Chatterbox weights to Hugging Face. Our pipeline started using them without a single config change.

    28:49 · 10 Oct 2026
  15. 15

    Why Voice Clones Lisp: Sibilants, Codecs, and the Sounds We Lose

    Sibilants and plosives are the most fragile sounds in speech — and every stage of the audio chain is quietly built to destroy them.

    23:17 · 10 Oct 2026
  16. 16

    Hebrew in Latin Letters: A TTS Pipeline Fix

    A token classifier that finds Hebrew words written in Latin letters so TTS stops mangling them — built for under $3.

    33:28 · 15 Oct 2026
  17. 17

    Why Your Voice Clone Sounds American

    Your cloned voice drifts toward American English. Here's what's actually happening — and why "neutral" is a myth.

    21:58 · 21 Oct 2026
  18. 18

    Voice Cloning: 10 Seconds to Steal Your Voice

    Ten seconds of audio is all it takes to clone a voice. Here's what the law actually protects — and what it doesn't.

    21:23 · 21 Oct 2026
  19. 19

    How Voice Cloning Works From Six Seconds of Audio

    Six seconds of reference audio is all Chatterbox needs. The real work happened in the half-million hours of training before you showed up.

    21:54 · 21 Oct 2026
  20. 20

    Teaching a TTS Model His Own Accent

    One man fine-tuned a text-to-speech model on his own voice to get Irish-accented English that can say Hebrew words mid-sentence.

    21:53 · 22 Oct 2026
  21. 21

    Me and My Voice Clone

    Daniel talks to his own voice clone. He recorded his lines on a phone; the clone's lines are Meorav v2, a model trained on 88 minutes of his voice.

    10:10 · 22 Oct 2026
  22. 22

    Benchmarking a TTS Model on Your Own GPU

    Real-time factor, warm-up artifacts, and why an 8-bit quantized speech model might not run any faster.

    24:25 · 22 Oct 2026
  23. 23

    Talking to Your Own Voice Clone

    What actually happens when you sit down and talk with an AI clone of your own voice — and what Evan Ratliff's Shell Game revealed.

    22:46 · 22 Oct 2026
  24. 24

    Why Synthetic Speech Needs Fake Room Noise

    Synthetic voices can drop to digital black between sentences — so engineers add fake room tone to make the silence sound real.

    20:38 · 23 Oct 2026