—
FireRedTeam
FireRedTeam is tracked for AI work in —. Shown below: 6 models.
$50M
Listed valuation
- Listed models
- 6
Figures and classifications reflect imported catalog records, not live company reporting.
Models
6
-
FireRed-OCR Gen 3 Multimodal
A framework that specializes large vision-language models into pixel-precise structural document parsing models.
- Image text extraction
- Text extraction
- Image and document analysis
-
FireRed Image Edit Gen 3 Image
A general-purpose image editing model aimed at high-fidelity, consistent instruction-based edits.
- Image generation
- Image enhancement
-
FireRed OpenStoryline Gen 4 Video
An AI video editing agent that turns natural-language intent into an editing workflow via planning and tool orchestration.
- Video enhancement
- Video repurposing
- Video production guidance
-
FireRedChat Gen 3 Multimodal
A fully self-hosted system for building real-time, full-duplex voice AI agents.
- Voice chatting
- Speech to speech
- Voice assistants
-
FireRedTTS 2 Gen 4 Audio
A long-form streaming TTS system for multi-speaker dialogue generation.
- Text to speech
- Voice cloning
-
FireRedASR2S Gen 4 Audio
An industrial-grade all-in-one ASR system combining ASR, VAD, LID, and punctuation modules.
- Voice recognition
- Speech to speech
- Voice transcription
In the catalogs
5
Repositories
- CQ-DINO Mitigating Gradient Dilution via Category Queries for Vast Vocabulary Object Detection
- FireRedASR2S FireRedASR2S is a SOTA Industrial-Grade All-in-One ASR system with ASR, VAD, LID, and Punc modules. FireRedAS…
- FireRedTTS2 Long-form streaming TTS system for multi-speaker dialogue generation
- FireRedTTS3 FireRedTTS3: Multilingual and Multi-Dialect Voice Cloning with Instruction-Guided Voice Design and Speech Edi…
Demos
- FireRed-Image-Edit-1.1 FireRed-Image-Edit-1.0 · running · License apache-2.0
Source rankings
Imported positions; not an independent quality score.
- Overall Rank#2061