{"schema":"postcutoff/event@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/e/2025-07-24-bytedance-seed-liveinterpret-2/","md":"https://postcutoff.com/e/2025-07-24-bytedance-seed-liveinterpret-2/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"2025-07-24-bytedance-seed-liveinterpret-2","date":"2025-07-24","date_precision":"day","short_title":"ByteDance's LiveInterpret 2.0 interprets Chinese-English simultaneously in your own voice","deck":null,"takeaway":"On 2025-07-24 ByteDance's Seed team released Seed LiveInterpret 2.0, an end-to-end speech-to-speech simultaneous interpretation model for Chinese<->English that speaks the translation in the speaker's cloned voice about 2.5-3 s behind.","category":"model-release","category_label":"Model releases","importance":3,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":[{"n":1,"title":"ByteDance Seed blog - Seed LiveInterpret 2.0 released","url":"https://seed.bytedance.com/en/blog/seed-liveinterpret-2-0-released-an-end-to-end-simultaneous-interpretation-model-featuring-ultra-high-accuracy-close-to-human-interpreters-low-latency-of-3-seconds-and-real-time-voice-cloning","type":"official","group":"primary","domain":"seed.bytedance.com"},{"n":2,"title":"arXiv 2507.17527 - Seed LiveInterpret 2.0 technical report","url":"https://arxiv.org/abs/2507.17527","type":"paper","group":"primary","domain":"arxiv.org"},{"n":3,"title":"Volcano Engine console - simultaneous interpretation demo","url":"https://console.volcengine.com/ark/region:ark+cn-beijing/experience/voice?type=SI","type":"docs","group":"primary","domain":"console.volcengine.com"}],"official":3,"filed":"2026-09-29","updated":"2026-09-29","orgs":["ByteDance Seed"],"title":"ByteDance Seed LiveInterpret 2.0: end-to-end Chinese-English simultaneous interpretation in your own voice, ~3 s behind","summary":"On 2025-07-24 ByteDance's Seed team released Seed LiveInterpret 2.0, an end-to-end speech-to-speech simultaneous interpretation model for Chinese<->English that speaks the translation in the speaker's cloned voice about 2.5-3 s behind. In ByteDance's human evaluations it came close to professional interpreters and far ahead of other systems. It shipped on Volcano Engine as \"Doubao - Simultaneous Interpretation 2.0\".","key_facts":["Latency: ~2.21 s first-word (speech-to-text) and ~2.53 s (speech-to-speech), which ByteDance says is 60-70% lower than cascaded systems (down from nearly 10 s)","Accuracy: >70% in multi-speaker and >80% in single-speaker settings; human-eval score 74.8/100 (speech-to-text) vs 47.3 for the runner-up baseline; 66.3/100 speech-to-speech","Real-time zero-shot voice cloning of each speaker; large-scale pretraining plus reinforcement learning to trade accuracy against latency","Paper: arXiv 2507.17527 'Seed LiveInterpret 2.0: End-to-end Simultaneous Speech-to-speech Translation with Your Voice'","Available on Volcano Engine (Ark console, 'Doubao - Simultaneous Interpretation 2.0'); planned for ByteDance's Ola Friend earbuds from end of Aug 2025. Public API model id and pricing not verified"],"key_numbers":[],"tags":["voice","speech","translation","simultaneous-interpretation","voice-cloning","china"],"science":null,"body_md":"## What happened\n\nByteDance replaced the usual ASR -> MT -> TTS cascade with a single end-to-end model that listens, translates and speaks\nat the same time, and renders each speaker's translation in their own cloned voice.\n\n## Why it matters\n\nIt was one of the first product-grade end-to-end simultaneous interpreters. It came roughly ten months before OpenAI's\ngpt-realtime-translate (May 2026), Google's Gemini 3.5 Live Translate (June 2026) and Alibaba's Qwen3.8-LiveTranslate\n(Sept 2026). All accuracy figures are ByteDance's own evaluations. It covers only Chinese and English.","disputed":[],"related":[{"id":"2026-08-05-bytedance-seedrealtime","url":"https://postcutoff.com/e/2026-08-05-bytedance-seedrealtime/","date":"2026-08-05","date_precision":"day","short_title":"ByteDance deploys SeedRealtime, a native audio-visual full-duplex model, in the Doubao app","deck":null,"takeaway":"It puts end-to-end \"see, hear and talk at once\" interaction in front of a mass consumer audience.","category":"model-release","category_label":"Model releases","importance":3,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":4,"official":3,"filed":"2026-09-29","updated":"2026-09-29","orgs":["ByteDance"]},{"id":"2026-06-09-gemini-3-5-live-translate","url":"https://postcutoff.com/e/2026-06-09-gemini-3-5-live-translate/","date":"2026-06-09","date_precision":"day","short_title":"Google launches Gemini 3.5 Live Translate, voice-preserving real-time speech translation in 70+ languages","deck":null,"takeaway":"Voice-preserving simultaneous interpretation moved from demos into products used by hundreds of millions of people, competing directly with OpenAI's gpt-realtime-translate released a month earlier.","category":"model-release","category_label":"Model releases","importance":3,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":4,"official":4,"filed":"2026-09-29","updated":"2026-09-29","orgs":["Google"]},{"id":"2026-05-07-openai-gpt-realtime-2-translate-whisper","url":"https://postcutoff.com/e/2026-05-07-openai-gpt-realtime-2-translate-whisper/","date":"2026-05-07","date_precision":"day","short_title":"OpenAI releases GPT-Realtime-2, GPT-Realtime-Translate and GPT-Realtime-Whisper","deck":null,"takeaway":"Reasoning moved into the low-latency voice loop instead of being bolted on via a separate text model, and live translation became a standalone API product, a month before Google's Gemini 3.5 Live Translate.","category":"model-release","category_label":"Model releases","importance":3,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":7,"official":5,"filed":"2026-09-29","updated":"2026-09-29","orgs":["OpenAI"]}],"people":[],"posts":[],"videos":[],"models":[],"changes":[{"date":"2026-09-29","type":"filed","text":"Created"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-09-29","run":null,"sources_read":null,"updated":"2026-09-29","human_review":null,"version":{"date":"2026-10-07"}},"gaps":[{"model_id":"gpt-6-astra","name":"GPT-6 Astra","cutoff":"2026-04","days_after":null,"in_training_data":true},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":null,"in_training_data":true},{"model_id":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","cutoff":"2026-03","days_after":null,"in_training_data":true},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":null,"in_training_data":true}],"short_url":null}