tweetindex
RU

Karan Goel

@krandiash · San Francisco, CA · joined 24 Jan 2010

founder ceo @cartesia, derp learned @stanfordailab @mldcmu @iitdelhi

20 643Followers
1 029Following
2 107Posts total
7.9MViews on collected posts

Последние посты

@krandiash My favorite model! Can’t wait emotions tags on none English voices (like French ;) 101 views · 1 likes · 0 reposts · 0 replies Open on X →
Super cool to see we're #2 on this new benchmark out of the box (#1 soon) This makes Ink-2 a great fit for consumer apps that are aimed at everyday interactions (and it runs real-time) 5.8K views · 54 likes · 1 reposts · 1 replies Open on X →
@krandiash TTS models are becoming more and more commoditized, and I still wonder what innovation is left in building the model. Of course, the field isn’t dominated by anyone yet, but there are already so many models. 60 views · 0 likes · 0 reposts · 0 replies Open on X →
@krandiash Karan, hope the next model goes beyond SSML. For voice agents where latency is critical, voice dictation via a prompt is also not practical like the Gemini 3.1 TTS supports because the LLM model will have to first generate the direction prompt before the actual answer 153 views · 0 likes · 0 reposts · 0 replies Open on X →
VoiceCodeBench is now live on Vals, and GPT Live Transcribe takes the #1 spot. @besimple_ai created VoiceCodeBench, which measures how well speech-to-text models handle structured values in English workplace speech. https://t.co/pVwfApwWHy
13K views · 37 likes · 6 reposts · 2 replies Open on X →
Our new TTS model Sonic-3.6 is now GA We went into preview last week as the #1 model on AA and it's been great to see early users back this up Overwhelmingly positive feedback, so much so that we graduated 3.6 to GA within a week And yes, the next model is cooking 🧑‍🍳 221.4K views · 379 likes · 97 reposts · 9 replies Open on X →
At Cartesia, our #1 value is "Get the fundamentals right". This value has been with us since Day 0. It shaped the research @_albertgu led during our PhDs: rather than using the same algorithms & architectures for every problem, he asked whether they were the right tool for the 17.9K views · 152 likes · 25 reposts · 8 replies Open on X →
Introducing Sonic-3.6: our most lifelike TTS yet, and another step change in naturalness across 44 languages. Just three months after our Sonic-3.5 launch, we've made fundamental model improvements based on feedback from the teams building on Sonic. We're #1 on @ArtificialAnlys
88.5K views · 663 likes · 73 reposts · 39 replies Open on X →
Happy 80th to 🇮🇳 Narrated by our best model yet 17.1K views · 482 likes · 19 reposts · 5 replies Open on X →
A very happy 80th Independence Day to India, from team Cartesia! 🇮🇳 Coming closer to home with Sonic 3.6, we're making every one of India's languages more natural, expressive, and accurate: - Hindi that flows the way you speak it - Hinglish that switches without missing a beat
0:49
110.8K views · 525 likes · 224 reposts · 90 replies Open on X →
Try a call with a real voice agent and sign up for the promo here! https://t.co/3OW8Pk4mcs 64K views · 49 likes · 1 reposts · 3 replies Open on X →
@krandiash its so hard to make a text-to-speech model with such a sub-300ms median ttft (time to first token). big big congrats! 3.4K views · 30 likes · 0 reposts · 1 replies Open on X →
We’ve seen incredible traction this year, with enterprises transforming every part of their operations with Voice AI. We’re sharing what we’ve learned and are giving away a guide to the top 10 enterprise use cases for Voice AI. Retweet and comment "CARTESIA" on the main video ht
0:13
118.2K views · 127 likes · 11 reposts · 33 replies Open on X →
If you switch to Cartesia from your existing provider, three months are on us. Hear the difference today. 👇🏻 https://t.co/xufoSwZRg3
0:53
152.3K views · 167 likes · 7 reposts · 9 replies Open on X →
We released Sonic-3.5 and Ink-2, the #1 streaming models for text to speech and speech to text you can use in your voice agents today. New architectures enable new frontiers for speed and quality. We're now the only provider to have #1 models for both speaking and listening. ht
2:47
7.1M views · 2.6K likes · 563 reposts · 735 replies Open on X →

На фоне аккаунтов своего размера

15 постов за последние 90 дней рядом с диапазоном 10K–100K подписчиков. показывается широко, но откликается мало кто.

Медианные просмотры17 851этот аккаунт980медиана для 10K–100K
Охват, %86.47%этот аккаунт3.51%медиана для 10K–100K
Вовлечённость, %0.39%этот аккаунт1.92%медиана для 10K–100K
ПоказательЭтот аккаунтМедиана для 10K–100KОтношение
Медианные просмотры на пост17 85198018.2×
Охват (просмотры ÷ подписчики)86.47%3.51%24.6×
Вовлечённость0.39%1.92%0.20×

Другие в этом диапазоне →   Сравнить с другим аккаунтом →   Как считаются эти ориентиры →

Growth & engagement

How the posts we collected actually performed: views and reaction rate post by post, what the audience did with them, and where the follower count goes.

Views per post

152.3K15 Jun
118.2K
3.4K
64K16 Jun
110.8K15 Aug
17.1K
88.5K17 Aug
17.9K
221.4K27 Aug
13K
15328 Aug
60
5.8K
101

Last 14 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

0.12%15 Jun
0.15%
0.92%
0.08%16 Jun
0.76%15 Aug
2.96%
0.90%17 Aug
1.06%
0.22%27 Aug
0.39%
0.00%28 Aug
0.00%
0.97%
0.99%

Reactions — likes, reposts, replies and quotes — divided by views. Median for 10K–100K accounts is 1.92%.

What the audience does

Likes55.3%5 281 in total
Reposts10.8%1 027 in total
Replies9.8%935 in total
Quotes2.1%200 in total
Bookmarks22.0%2 099 in total

Share of every reaction we collected for this account. Replies mean argument, reposts mean endorsement, bookmarks mean the post was worth keeping.

The follower curve appears once this account has two daily snapshots — we take one a day, and this one is on its first.

Похожие аккаунты