Gnani AI trains on 14M hours of telephonic audio; Eloelo unveils Dolphin AI for multi-shot video
CurieuxExplorer · x · 2026-10-05
- Gnani AI (Vachana): Indic speech-to-text and voice cloning trained on large real-world Indian audio. Its Prisma v2.5 STT is trained on 14M+ hours of telephonic audio and ranks #1 in 8 of 9 Indian languages on Kathbath Noisy 8kHz; Timbre v2.5 TTS covers 21+ languages with <200ms P95 latency. Built for contact centers, banks, and Indian-language apps.
- Dolphin AI (Eloelo): announced at FICCI FRAMES 2026 by founder Saurabh Pandey, it turns a script into multi-shot video with character, voice, and wardrobe continuity—targeting creators, ad teams, and micro-drama studios needing clips beyond 8–10 seconds.
More from Multimodal
- Ego2Act benchmark tests 6 SOTA video models on goal-directed action execution — mohitban47 · 2026-10-05
- NihonSub: Open-Source Real-Time Anime Subtitle Engine Built on Whisper + DeepSeek — Grand_Marionberry115 · 2026-10-05
- RAT KING: A Character Consistency Test of MiniMax H3 — malcolmrey · 2026-10-05
- ElevenLabs launches The Search, a $100K contest to find the world's catchiest ad jingle — lukeharries · 2026-10-05
- Runway Teases Behind-the-Scenes of Jon Wertheim's New 60 Minutes Title Sequence — c_valenzuelab · 2026-10-05
- Donut Breakfast Ad Made With Google's Omni Video Model, Prompt Shared — michaelrabone · 2026-10-05