| The people behind the benchmarks. Jakub Piotr Cłapa is Hume's Head of Research.
"LLMs are only trained on what we coul… |
@hume_ai |
Company |
Original |
2026-10-20 |
700 |
1 |
0 |
0 |
0 |
0 |
| Grok Voice 3.0 from @xai launched this week, making some meaningful gains on naturalness. Sounding tangibly more human … |
@hume_ai |
Company |
Original |
2026-10-16 |
1,471 |
14 |
2 |
2 |
0 |
3 |
| @ElevenLabs v4 Turbo and v4 just joined the Real World VoiceEQ leaderboard at 3rd and 4th of 38.
We ran both through … |
@hume_ai |
Company |
Original |
2026-10-09 |
948 |
1 |
1 |
1 |
0 |
5 |
| Someone says "I'm fine." You know they aren't.
You heard it - the pause, the flat tone. Voice AI doesn't. It all gets d… |
@hume_ai |
Company |
Original |
2026-10-06 |
9,953 |
68 |
9 |
26 |
3 |
22 |
| Text-to-speech was built to read a single voice aloud. Now it's being asked to hold a conversation between two, and tha… |
@hume_ai |
Company |
Original |
2026-09-29 |
3,423 |
38 |
5 |
5 |
0 |
41 |
| New scores are up on the Real World VoiceEQ text-to-speech board, plus two new scoring metrics and a new voice controll… |
@hume_ai |
Company |
Original |
2026-09-23 |
2,718 |
35 |
8 |
3 |
0 |
13 |
| A result from the Voice Controllability leaderboard we published today:
Fish's voice design model won nearly every head… |
@hume_ai |
Company |
Original |
2026-09-17 |
3,034 |
23 |
1 |
2 |
2 |
15 |
| Congratulations to the @OpenAI team on the GPT-Live-1 launch.
Here is the early read from our RWVoiceEQ STS evals.
Vo… |
@hume_ai |
Company |
Original |
2026-09-14 |
7,960 |
77 |
3 |
8 |
2 |
37 |
| We asked 11 voice cloning models to copy the same 25 voices, then asked real people: is that the same person?
The most… |
@hume_ai |
Company |
Original |
2026-09-10 |
14,547 |
79 |
17 |
3 |
4 |
63 |
| Sounding human is the third most important factor in voice AI. Not the first.
Our CEO Andrew Ettinger (@ahe23) joined … |
@hume_ai |
Company |
Original |
2026-09-02 |
9,087 |
20 |
2 |
2 |
1 |
13 |
| RT @ahe23: A researcher on our team showed me a clip last month that stuck with me.
A speaker on a European Parliament… |
@hume_ai |
Company |
Repost |
2026-08-22 |
209 |
0 |
2 |
0 |
0 |
0 |
| For anyone who saved the paper and hasn't opened it :) https://t.co/rGpdrX8njs |
@hume_ai |
Company |
Quote |
2026-08-22 |
3,203 |
18 |
3 |
0 |
0 |
8 |
| We silenced a number in the benchmark audio. It was never spoken.
Some of the highest-scoring speech recognition model… |
@hume_ai |
Company |
Original |
2026-08-21 |
7,632 |
65 |
11 |
10 |
10 |
19 |
| Today Hume is introducing Real World VoiceEQ: a benchmark for measuring the human quality of voice AI across 40+ propri… |
@hume_ai |
Company |
Original |
2026-07-15 |
245,096 |
159 |
42 |
21 |
9 |
89 |
| Today, voice models have no problem generating “angry” or “sad” expressions.
But ask for:
→ bored + fast
→ joy + shy… |
@hume_ai |
Company |
Original |
2026-05-27 |
2,010 |
31 |
3 |
4 |
0 |
14 |
| We’re excited to launch the 2026 ACII Dyadic Contest (DaiKon) Workshop & Challenge—a new benchmark for modeling emotion… |
@hume_ai |
Company |
Original |
2026-04-08 |
3,436 |
40 |
9 |
7 |
1 |
21 |
| Today, we're shipping MLX support for TADA, our open-source text-to-speech model, which means the entire pipeline (LLM,… |
@hume_ai |
Company |
Original |
2026-03-27 |
24,709 |
304 |
28 |
11 |
2 |
347 |
| Today we're releasing our first open source TTS model, TADA!
TADA (Text Audio Dual Alignment) is a speech-language mod… |
@hume_ai |
Company |
Original |
2026-03-10 |
270,914 |
2,904 |
305 |
102 |
44 |
2,621 |
| Today, we're announcing significant new traction in our voice AI research and development partnerships.
Over the past … |
@hume_ai |
Company |
Original |
2026-01-22 |
12,634 |
140 |
10 |
10 |
4 |
46 |
| Can you convince Santa to take a villain off the naughty list? Visit https://t.co/1aTFQnf9O0 for a whimsical voice AI p… |
@hume_ai |
Company |
Original |
2025-12-16 |
2,687 |
16 |
1 |
1 |
0 |
7 |
| The Control Plane API is now live for Hume's EVI (Empathic Voice Interface) — enabling fast & seamless creation of phon… |
@hume_ai |
Company |
Original |
2025-11-25 |
2,551 |
17 |
2 |
3 |
0 |
5 |
| Today we honor Dr. Paul Ekman, whose pioneering work on how we express and perceive emotion laid much of the groundwork… |
@hume_ai |
Company |
Original |
2025-11-20 |
2,458 |
21 |
2 |
1 |
0 |
4 |
| One performance, infinite voices.
Voice Conversion is now live on Hume’s creator studio and API!
Generate the same pa… |
@hume_ai |
Company |
Original |
2025-11-06 |
20,013 |
167 |
33 |
20 |
8 |
135 |
| Why are phone numbers so hard for voice AI?📞🤖
Did you know that reading out something as simple as 555-010-2314 is a w… |
@hume_ai |
Company |
Original |
2025-10-30 |
4,978 |
54 |
7 |
4 |
0 |
25 |
