Assertion Contradicted AI assessment confidence: 95% certainty 3/5 debate potential 2/5

Shulman: Bark was the first open-source transformer-based TTS model

Mikey Shulman · Making Transformers Sing - with Mikey Shulman of Suno · Mar 14, 2024 · at 15:48

Mikey Shulman, co-founder of Suno, discusses the origins of Bark, Suno's open-source generative audio and text-to-speech model.

0:00 / 0:09exact quote · 9.3s

▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark

“As far as I know there was no other certainly not in the open source text to speech that was kind of transformer based.”

quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →

The claim, plainly

Prior to Suno releasing Bark, there was no other open-source text-to-speech system that was transformer-based.

a quote alone can be ambiguous, so this restates it with the references and context of the conversation around it resolved. AI-written; the tape below the player is the source.

Assessment

Suno open-sourced Bark in April 2023. Multiple open-source, transformer-based text-to-speech (TTS) systems publicly predated Bark by months to years. Notable examples include Transformer TTS (open-sourced in 2019), FastSpeech and FastSpeech 2 (integrated into open-source repositories such as ESPnet-TTS and TensorFlowTTS between 2019 and 2021), and TorToiSe TTS (an autoregressive transformer/GPT-style TTS model open-sourced by James Betker in March–April 2022).

Suno publicly open-sourced the Bark repository in April 2023 under the MIT license.
TorToiSe TTS ('neonbjb/tortoise-tts'), an open-source autoregressive transformer-based TTS system, was released in March–April 2022.
ESPnet-TTS and open-source implementations of FastSpeech and Transformer TTS were publicly released between 2019 and 2021.

Checked against

[1] localaimaster.com [2] clawbot.ai [3] github.io [4] arxiv.org [5] github.com [6] github.com [7] github.io [8] researchgate.net

"tortoise-tts" "2022" github "Transformer-TTS" "2019" OR "2020" github "suno-ai/bark" github release date "Transformer TTS" github release date "ESPnet" "Transformer" TTS "2019" OR "2020" "FastSpeech" "2019" github "FastSpeech" "transformer" github release date "tortoise-tts" github release date

assessed as of 2026-09-03

This assessment is an AI reading of a public statement, made against the cited references with the confidence shown. It can be wrong. The quote, the tape and the references are all on this page; if something is off, use report an error below. full disclaimer →

Mentioned

Bark Suno text-to-speech

⚑ Spot an error? Report it

More from Mikey Shulman

Disclosure

Shulman: Suno does not only train its models on music

“People are always surprised to learn that we don't only train on music.”

Mikey Shulman Mar 14, 2024 ▶ 8:40 Making Transformers Sing - with Mikey Shulman of Suno

Disclosure

Shulman: Suno prohibits users from generating songs using copyrighted lyrics

“We actually don't let you do that. And it's because if you're taking someone else's lyrics, you didn't own those. You don't have the publishing rights to those. You can't remake that song.”

Mikey Shulman Mar 14, 2024 ▶ 40:57 Making Transformers Sing - with Mikey Shulman of Suno

Prediction Not checkable as stated

Shulman: AI song covers are viral novelties, not music's future

“And I think this stuff is very viral, but I actually really don't think that this is how people want to interact with music in the future.”

Mikey Shulman Mar 14, 2024 ▶ 41:26 Making Transformers Sing - with Mikey Shulman of Suno

Opinion

Shulman: Generative audio AI lags text and images by one to two years

“So I think very roughly you can think audio is like one to two years behind images and text. And so you kind of have to think today like text was in 20, 22 or something like this.”

Mikey Shulman Mar 14, 2024 ▶ 3:00 Making Transformers Sing - with Mikey Shulman of Suno

Disclosure

Suno avoids hardcoding musical rules into its generative models

“We try not to impose anything about music or audio in general into the model, and we kind of let the models learn things by themselves.”

Mikey Shulman Mar 14, 2024 ▶ 5:42 Making Transformers Sing - with Mikey Shulman of Suno

Insight

Shulman: Understanding of music scaling laws is far behind text

“I don't think we know these things nearly as well as they're known in text. We have some notions of some of the scaling laws here, but I think yeah, we're just so, so far behind.”

Mikey Shulman Mar 14, 2024 ▶ 8:28 Making Transformers Sing - with Mikey Shulman of Suno

Shulman: Bark was the first open-source transformer-based TTS model

More from Mikey Shulman

Turn any episode into a week of clips.