Average Ratings 1 Rating
Average Ratings 0 Ratings
Description
Muse Spark 1.2 is Meta’s newest coding-focused model, released alongside Muse Code as part of Meta’s AI developer platform. The model improves on Muse Spark 1.1 with stronger code generation, complex debugging, codebase understanding, and full developer workflow performance. Muse Spark 1.2 powers Muse Code, a terminal coding agent that can plan changes, write code, validate results, and coordinate persistent background subagents. The model was co-trained with Muse Code so it performs well inside the agentic coding runtime and tool environment. Its training included scaled coding compute, broader training environment diversity, rejection-sampled harness trajectories, recipe optimizations, and Muse Code toolset integration. Muse Spark 1.2 is designed for long-horizon coding tasks such as whole-repository generation, large end-to-end projects, auto-research, and extended optimization work. It uses planning to sequence work, goal conditioning to stay aligned with the user’s objective, and context compaction to preserve useful knowledge over long sessions. The model also benefits from a self-improvement loop where Muse Spark 1.1 generated challenging coding environments and instruction-following templates for training. By combining coding specialization, agentic workflow support, long-horizon training, subagent compatibility, and Meta Model API availability, Muse Spark 1.2 helps developers build, debug, and optimize software more effectively.
Description
Muse Voice Transcribe represents Meta’s inaugural venture into real-time audio perception, providing instantaneous automatic speech recognition (ASR), speaker diarization, and endpointing capabilities. This autoregressive multimodal model, part of the Muse Spark series, analyzes audio segments of 80 milliseconds and makes real-time decisions on whether to keep listening or to convert the spoken words into text. The adaptive delay mechanism allows it to adjust the audio context utilized for each word according to the complexity of the speech, thus optimizing the balance between transcription precision and response time. With training encompassing over 70 languages, 25 of which were rigorously validated at the time of its release, the model also seamlessly accommodates arbitrary code-switching, allowing transitions within and across sentences. Furthermore, language, keyword, and contextual biasing features enhance the recognition capabilities for specific names, locations, contacts, or specialized terms. The streaming diarization functionality enables the model to recognize shifts in speakers and can differentiate between more than 20 individual voices. Additionally, the endpointing feature is adept at identifying the commencement of speech and knowing when a user has completed their statement, ensuring a fluid interaction experience. Overall, Muse Voice Transcribe stands out as a cutting-edge tool in the realm of speech recognition technology, merging advanced features with user-friendly application.
API Access
Has API
Yes
API Access
Has API
Yes
Integrations
Bash
Yes
C
Yes
Claude Agent SDK
Yes
Claude Code
Yes
Continue
Yes
Facebook
Yes
HTML
Yes
Instagram
Yes
LangChain
Yes
Meta AI
Yes
Integrations
Bash
No
C
No
Claude Agent SDK
No
Claude Code
No
Continue
No
Facebook
No
HTML
No
Instagram
No
LangChain
No
Meta AI
No
Pricing Details
$1.25 per 1M tokens (input)
$1.25 per million tokens in input, and $4.25 per million tokens of output
Free Trial
Yes
Free Version
No
Pricing Details
No price information available.
Free Trial
Yes
Free Version
No
Deployment
Web-Based
Yes
On-Premises
No
iPhone App
No
iPad App
No
Android App
No
Windows
No
Mac
No
Linux
No
Chromebook
No
Deployment
Web-Based
Yes
On-Premises
No
iPhone App
No
iPad App
No
Android App
No
Windows
No
Mac
No
Linux
No
Chromebook
No
Customer Support
Business Hours
No
Live Rep (24/7)
No
Online Support
Yes
Customer Support
Business Hours
No
Live Rep (24/7)
No
Online Support
Yes
Types of Training
Training Docs
Yes
Webinars
No
Live Training (Online)
No
In Person
No
Types of Training
Training Docs
Yes
Webinars
No
Live Training (Online)
Yes
In Person
No
Vendor Details
Company Name
Meta
Founded
2004
Country
United States
Website
meta.ai
Vendor Details
Company Name
Meta
Founded
2004
Country
United States
Website
research.meta.ai/blog/introducing-muse-voice-transcribe