mirror of
https://github.com/hanzoai/site.git
synced 2026-11-20 21:21:13 +00:00
The browser capture freezes the running demo at a random moment (STEP 3/50 before, STEP 9/50 on this capture). content/live/iro.json's one readout entry now holds the frame hanzo.ai server-renders on every request, the same line content/pages/iro.html (Hanzo's server copy) already carries: FLOW-MATCHING CONVERGENCE: STEP 38/50 · CFG: 7.0. parity /iro OK, /koe OK. Co-Authored-By: Claude Opus 5.5 <[email protected]> Claude-Session: https://claude.ai/code/session_01P5YBdycWh75FpA2M9CWJ5d
1 line
2.1 KiB
JSON
1 line
2.1 KiB
JSON
{"text":["Voice","Koe 1","Performance in every word.","Directable speech synthesis, character performances, dubbing and multilingual dialogue.","Request access","Try it in Design","studio.hanzo.ai /","koe-1","koe","example","FLOW-MATCHING ACOUSTIC STAGE · STREAMING PHONEMES","00:0","80","/ 00:05.00 · TTFT: 180ms","/h/","/æ/","/n/","/z/","/oʊ/","ACTING PRESET:","Cinematic Dramatic","Intimate Documentary","Gritty Character","Warm Commercial","Zero-Shot Cloning","Reference Audio","3.0s Clean Sample","Sub-Second Latency","First Token","< 200ms","Synthesis Engine","Hanzo Koe-1 Engine","Neural Flow-Matching","An example of the canvas in Hanzo Design. Generation runs on Hanzo Cloud.","Capabilities","What Koe does","Director-grade emotional modulation","Direct nuances in tone: breath control, hesitation, whispers, intense delivery, irony, and pitch contour through natural language instructions.","Cross-lingual voice cloning","Preserves vocal identity, formant fingerprint and emotional timbre across languages and regional dialects.","Viseme-synchronized dubbing","Phoneme timing alignment matched to video mouth shapes and facial cadence for localization.","Actor likeness rights","Every synthesized voice carries an imperceptible cryptographic watermark, and its provenance is logged.","In production","Where Koe fits","Localization","Actor-preserving film dubbing","Dub episodic television and movies into international languages while retaining the original actor’s voice characteristics.","Game dialogue","Real-time branching character speech","Deliver thousands of hours of high-performance character dialogue in video games without recording bottlenecks.","Audiobooks and podcasts","Multi-voice dramatic performances","Cast an entire ensemble of distinct characters from a single manuscript with consistent chapter-to-chapter character voices.","Research preview","Try Koe on your own work","Samples of Koe's own output publish only after blind review, so the pictures here are illustrations. A studio can apply now to test it in its own pipeline.","Every model"],"links":["/beta/research","/design","/research-access?models=koe","/models"]} |