Unverified50% confidenceFactExact time
Audio 2B accepts text or speech input and outputs text, speech, or both in sync; it supports tool calling, voice chat and reasoning in 18 languages.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/4/2026
First Seen
Valid until: 2/2/2027
Sources
Running Audio and Vision Locally with a 2B Model: LFM3 Hands-On Revealed
bilibili枫叶边城11/4/2026
Related Entities
Related Claims
UnverifiedVoiceCap generates meeting summaries, action items, and decision records in the same language as the original audio, maintaining language consistency.77% similarUnverifiedMusic and sound effects models reuse the generateSpeech interface, describing the target sound rather than the text to be read aloud in the text field, so callers do not need to learn a new request format, and authentication, billing, retry, and tracing logic remain consistent.76% similarVerifiedFor voice agents, multimodal large models must support not only voice, images, text, and video as inputs, but also voice as output.75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1134829API
curl https://kongchang.com/api/v1/knowledge/claims/1134829MCP
get_claim(id=1134829)