Mini toolsSeed models
Browse all models from this model family.
ID
Model
Company
Type
Primary task
Open source
-
By ByteDanceSeed Audio 1.0 is ByteDance's universal audio generation model that creates voice, music, sound effects, and ambient soundscapes from text prompts. It supports zero-shot voice cloning from short audio references, multi-character dialogue generation in a single pass, and cross-lingual synthesis without fine-tuning. Accessible via Volcano Engine API.NewAudioReleased 18d ago
-
By ByteDanceDola-Seed-2.0-Preview is ByteDance Seedโs general-purpose multimodal model released for public evaluation on Arenaโs Text and Vision leaderboards.MultimodalReleased 4mo ago
-
By ByteDanceSeed 2.0 is described publicly only as a new ByteDance Seed language model for Doubao, but there is not yet any reliable, detailed public technical description of its architecture, context length, or training data that I can quote.MultimodalReleased 4mo ago
-
By ByteDanceSeed-Prover 1.5 is ByteDance Seedโs formal theorem-proving model for Lean, trained with agentic RL and test-time scaling to solve most undergraduate and many graduate-level competition problems.TextReleased 5mo ago
-
By ByteDanceGeneral-purpose agentic model that unifies LLM and VLM abilities with search, code execution and GUI control, designed to perceive text and images, reason over long contexts and autonomously carry out multi-step tasks.MultimodalReleased 6mo ago
-
By ByteDanceSeed-OSS-36B-Instruct is ByteDance Seedโs open-source 36B instruction model built for long-context work, reasoning, agents, and general-purpose developer use. ByteDance positions the Seed-OSS line as efficient for its scale, reporting strong open-benchmark results from 12T training tokens.MultimodalReleased 10mo ago
-
By ByteDanceSeed1.6 integrates multimodal capabilities, with "adaptive thinking" balancing model performance with reasoning capability.TextReleased 1y ago
-
By ByteDanceCompact vision-language foundation model from ByteDance Seed, combining a 532M vision encoder with a 20B-active MoE LLM to deliver strong image, video and GUI understanding and multimodal reasoning, with many SOTA results at low inference cost.MultimodalReleased 1y ago
-
By ByteDanceMixture-of-experts Seed1.5 (Doubao-1.5-pro) large language model that balances high performance with efficient inference, excelling at knowledge, coding and reasoning while using far fewer active parameters than comparable dense modelsMultimodalReleased 1y ago
