Launchscene
PricingSign in
Explore

Drop 3/15 Introducing Voice Arena's Speech Recognition (ASR) Benchmark. One benchmark for every use case of speech recognition. Dataset 1 is live: the Monsoon Conversational ASR Test Set… | Shobhit Banga

VoiceArena · Nov 2026 · 2:14 · AI-annotated

Length
2:14
Scenes
26 · 5.2 s avg
Product on screen
1:22
Features shown
5
Call to action
1:59 · 89%
Voiceover
Yes
00:00:00 / 02:14:02

VoiceArena’s 2:14 launch film runs 26 scenes, about 5.2 s each. The product shows up at 1:22 and 5 features are revealed. The call to action lands at 1:59 (89% in), over a voiceover. The video alternates a locked-off founder talking to camera with white motion-graphics slides that build element by element, numbering the benchmark's four criteria from 1/4 to 4/4 before the product reveal. Pacing is steady at about ten cuts a minute, with titles snapping from blur to focus and a glowing blue dot stamping each new card in step with the voiceover.

Footage neededEstimated needs: 1 capture group — your screens or recordings · 1 official logo — reused across the film · 18 filmed passages — shoot, supply or replace · 2 graphic passages — draw or supply

Is this your launch? to your site or press kit.

More like this

Drop 3/15 Introducing Voice Arena's Speech Recognition (ASR) Benchmark. One benchmark for every use case of speech recognition. Dataset 1 is live: the Monsoon Conversational ASR Test Set… | Shobhit Banga, scene by scene

· 26 scenes as text
  1. 01 · Hook · 0:00–0:06

    A man in a white t-shirt stands in a bright office with tall windows, speaking to camera and gesturing with both hands on a locked-off shot. A blue lower-third card slides in from the right with his name and title, then slides out.

    On-screen text: “Shobhit Banga”, “Co-Founder & CEO”, “Voice Arena”

    Camera: Static

  2. 02 · Hook · 0:06–0:09

    A man in a white T-shirt stands in a bright room with whiteboards and a window, talking and gesturing with both hands. A two-line caption appears top left while he speaks. The camera holds a locked-off medium shot of him on the right.

    On-screen text: “Dreaming up”, “an ASR benchmark”

    Camera: Static

  3. 03 · Feature reveal · 0:09–0:15

    A man in a white t-shirt stands in a bright office with tall windows, talking and gesturing with both hands toward the camera. White text reading 1/4 Every use case holds at the left edge, and a blue shield logo with a waveform mark stays in the top right corner.

    On-screen text: “1/4”, “Every use case”

    Camera: Static

  4. 04 · Feature reveal · 0:15–0:18

    A man in a white t-shirt stands in a bright room with whiteboards and tall windows, gesturing with both hands as he speaks off-axis. A small blue shield logo sits in the top right corner while white text overlays the left edge.

    On-screen text: “1/4”, “Every use case”, “Many datasets,”, “one benchmark”

    Camera: Static

  5. 05 · Feature reveal · 0:18–0:31

    A white slide under the headline 'Every use case of speech recognition' fills row by row with eight lavender cards, each stamped in by a moving blue dot in step with the voiceover. Each card pairs a flat icon with a title and caption, listing multi-speaker, call centre, entities, dictation, child speech, long-form, far-field, and a plus icon.

    On-screen text: “Every use case of speech recognition”, “Multi-speaker”, “Overlapping voices”, “Call centre”, “Phone audio at 8 kHz”, “Entities”, “Digits, passwords, names”, “Dictation”, “Speak it, see it typed”, “Child speech Young voices”

    Camera: Static

  6. 06 · Feature reveal · 0:31–0:32

    A man in a white shirt gestures mid-speech in a bright office with whiteboards and a window. On the left, a small index number sits above the words Every language in white. A blue shield logo with a waveform marks the top right corner.

    On-screen text: “2/4”, “Every language”

    Camera: Static

  7. 07 · Feature reveal · 0:32–0:37

    A man in a white t-shirt stands in a sunlit office, gesturing with both hands as he speaks. A dotted world map fades in on the left and lights up beside the headline, while a small blue shield logo sits in the top right corner.

    On-screen text: “2/4”, “Every language”, “For billions of people”

    Techniques: Particles

    Camera: Static

  8. 08 · Feature reveal · 0:37–0:41

    A man in a white shirt is interviewed in a bright room with tall windows, gesturing with both hands. On the left, a white caption block reads 2/4, Every language, For billions of people above a dotted world map, and 100+ languages fades in beneath it before the block fades out.

    On-screen text: “2/4”, “Every language”, “For billions of people”, “100+ languages”

    Camera: Static

  9. 09 · Feature reveal · 0:41–0:45

    A man in a white t-shirt speaks to the camera in a bright office, gesturing with both hands. A white label '3 / 4' and 'Public and private sets' sits on the left; a blue shield logo marks the upper right. The shot cuts to white at the end.

    On-screen text: “3 / 4”, “Public and private sets”

    Camera: Static

  10. 10 · Feature reveal · 0:45–0:56

    On a white background, a bold indigo headline sits above two side-by-side cards: a Private card with a lock icon and three blurred waveform rows, and a Public card with an eye icon and readable transcript lines. Short captions fade in beneath each card.

    On-screen text: “One test set, split in two”, “Audit it yourself”, “Check its accuracy and relevance”, “Kept out of training data”, “Lowers the chance of contamination”

    Camera: Static

  11. 11 · Feature reveal · 0:56–1:01

    A man in a white t-shirt sits at an office desk, gesturing with both hands as he speaks to camera. A white caption reads 4/4 Metrics per use case on the left, and a blue shield logo sits top right. The frame is locked off.

    On-screen text: “4/4”, “Metrics per use case”

    Camera: Static

  12. 12 · Feature reveal · 1:01–1:14

    On an off-white field, a dark indigo headline sits above two white rounded cards that build in sequence. The top card compares a reference and a model sentence, highlighting one swapped word, then a 20% metric fades in at right. A second card opens below and draws a branching Hindi word path ending in a check mark, with a 0% metric and an explanatory caption.

    On-screen text: “Real errors count. Valid spellings don't.”

    Camera: Static

  13. 13 · Feature reveal · 1:14–1:22

    A white slide fades in with the navy heading “Different use cases, different metrics.” Three numbered cards rise up in sequence, each pairing a metric with a small example: a highlighted word, Devanagari chips, a Booked pill. A navy “Beyond word error rate” badge fades in below.

    On-screen text: “Different use cases, different metrics”, “Word error rate”, “Words wrong out of words said”, “turn on the chicken lights”, “Said “kitchen”. One real error.”, “Dictation, captions”, “OIWER”, “Every valid spelling counts”, “अंग्रेजी”, “Three valid spellings, all correct', 'Languages with many ways to write', 'Task success rate', 'Did the job get done?', '“Book a table for four”', 'Booked', 'Vo”

    Techniques: Kinetic type

    Camera: Static

  14. 14 · Product intro · 1:22–1:29

    A man in a white t-shirt stands in a bright office with tall windows, gesturing as he talks. On the left, four checkmark bullet points stack in, then a two-line heading appears beneath them. A blue shield logo with a waveform sits in the top right corner.

    On-screen text: “Every use case”, “100+ languages”, “Public and private sets”, “Metrics per use case”, “Taking the first step”

    Camera: Static

  15. 15 · Product intro · 1:29–1:34

    On a pale lavender background, the VoiceArena.com logo sits above a large blue headline that snaps from a soft blur into sharp focus. A rounded blue 'Live today' badge with a white dot fades in below the headline.

    On-screen text: “VoiceArena.com”, “Speech Recognition Benchmark”, “Live today”

    Camera: Static

  16. 16 · Feature reveal · 1:34–1:42

    On a white background, a small outlined pill reads Dataset 1 while the title Monsoon scales in from a blur, followed by the subtitle Conversational ASR Test Set. A rounded card with two waveform tracks for Speaker A and Speaker B slides up, a vertical playhead sweeps left to right, and a dark pill caption Conversational speech in 5 languages drops in below.

    On-screen text: “Dataset 1”, “Monsoon”, “Conversational ASR Test Set”, “Conversational speech in 5 languages”, “VoiceArena.com”

    Techniques: Kinetic type, Masking

    Camera: Static

  17. 17 · Other · 1:42–1:49

    A man in a white t-shirt sits in a bright office, gesturing to camera. On the left a vertical timeline builds downward, a glowing dot lighting each node as Dataset 1 to 6 appear. A bold white headline then reads More languages. More use cases.

    On-screen text: “Dataset 1”, “Live”, “Dataset 2”, “Next few days”, “Dataset 3”, “Next few days”, “Dataset 4”, “Next few days”, “Dataset 5”, “Next few days Dataset 6 Next few days More languages. More use cases.”

    Techniques: Kinetic type

    Camera: Static

  18. 18 · Other · 1:49–1:53

    A man in a white t-shirt stands in a bright office with whiteboards and a window, gesturing with both hands while speaking. Two white labels, “Independent.” and “Third-party.”, appear stacked on the left.

    On-screen text: “Independent.”, “Third-party.”

    Camera: Static

  19. 19 · Other · 1:53–1:55

    A man in a white t-shirt stands center frame in a bright office with tall multi-pane windows, gesturing with both hands as he speaks to camera. Bold white text reads “Independent. Third-party.” on the left; a blue shield logo with sound bars sits top right.

    On-screen text: “Independent.”, “Third-party.”

    Camera: Static

  20. 20 · Other · 1:55–1:59

    A man in a white t-shirt sits in a sunlit office, gesturing with both hands as he speaks to the side. A static white headline and gray subline hold on the left, a blue shield mark sits top right. The camera is locked off.

    On-screen text: “Independent.”, “Third-party.”, “Trusted by academia and industry”

    Camera: Static

  21. 21 · CTA · 1:59–2:04

    A man in a white t-shirt sits in a bright office, gesturing with both hands while speaking. White text on the left fades in: “Public test sets on Hugging Face”, then “All 5 languages” appears below. A blue shield logo sits top right.

    On-screen text: “Public test sets”, “on Hugging Face”, “All 5 languages”

    Camera: Static

  22. 22 · CTA · 2:04–2:07

    A man in a white t-shirt talks and gestures in profile beside a white text block on the left. The shot cuts to a front view of him at a desk, hands clasped, as the text disappears.

    On-screen text: “Public test sets”, “on Hugging Face”, “All 5 languages”

    Camera: Static

  23. 23 · CTA · 2:07–2:09

    A man in a white t-shirt sits in a bright office, facing the camera and gesturing with both hands as he speaks. Large windows and office desks fill the background. A small blue shield logo holds the top right corner.

    Camera: Static

  24. 24 · CTA · 2:09–2:10

    A man in a white t-shirt stands in a sunlit office, smiling and gesturing with both open hands toward the camera. Behind him, large windows show greenery, and desks with chairs fill the right side of the frame.

    Camera: Static

  25. 25 · Outro · 2:10–2:11

    A shield icon with a waveform and the wordmark Voice Arena fade in at center on a pale gray background, while a small blurred blue dot drifts near the left edge.

    Camera: Static

  26. 26 · Outro · 2:11–2:14

    On a near-white field, the Voice Arena lockup, a shield icon holding an audio waveform beside the wordmark, sits left of center. It opens in soft periwinkle with a faint circular halo behind the shield; the halo fades and the mark deepens to solid navy, then holds.

    On-screen text: “Voice Arena”

    Camera: Static