Motorsport junkie 🏎️ AI Partnerships at @meta. (ex @pumaindia🇮🇳, @followloop🇦🇹)
Joined October 2009
- Tweets29.4K
- Following1.5K
- Followers1.4K
- Likes25K
Just got started with S04 of The Diplomat and I'm giddy already! My favourite thing on television in a long, long time. Just how I love this show, the writing and the actors!
Merin Mandanna retweeted
Muse Wonder is now available on @Cline, @Cloudflare, @Cognition, @Cursor_AI, @OpenRouter, @Oracle and @Vercel - with more partners coming soon.
We look forward to seeing what the community builds with Muse Wonder!
Start building 👉 bit.ly/47wMYCp
Merin Mandanna retweeted
Introducing Muse Wonder, our new family of frontier models with state of the art performance for personal and professional agentic work.
Merin Mandanna retweeted
Muse Voice Transcribe is now available as a plugin in LiveKit Agents.
Start building: docs.livekit.io/agents/model…
Muse Voice Transcribe from @AIatMeta @MetaforDevs is now live! You can now use Meta's new streaming STT model in LiveKit Agents, with real-time diarization for 20+ speakers.
Try Muse in LiveKit Agents: docs.livekit.io/agents/model…
Merin Mandanna retweeted
Muse Voice Transcribe was built for real-time voice agents, combining accuracy and low latency with diarization, keyword biasing, endpointing and mixed-language transcription.
Great to see it achieve the lowest semantic WER in Pipecat’s open-source benchmark 👏
Pipecat v1.9.0 is out today, with support for @AIatMeta's new Muse Voice Transcribe model.
Muse Voice Transcribe is a streaming speech-to-text model. It has the best (lowest) semantic word error rate of any model we've tested.
We maintain a public, open source test suite called the Pipecat STT benchmark. This benchmark measures how well an STT model performs in a voice agent pipeline. We calculate a "semantic word error rate" across 1,000 speech input fragments. Semantic WER ignores small differences in transcription that don't impact an LLM's understanding of user speech, and in our experience is a better proxy for STT model accuracy than the simpler WER algorithms used in most speech recognition benchmarks.
The other critical metric for a voice agent is latency. We measure latency as "time to final segment" of the transcription. You can think of this as how long it takes for the STT model to deliver a complete text transcription after the user finishes speaking. Muse Voice Transcribe's TTFS is very good, though its long tail TTFS is a bit higher than we'd like to see. (The Meta team says they are optimizing for natural, model-driven endpointing, which certainly makes sense.) The P50 TTFS is 392 milliseconds and the P95 is 1,292 milliseconds. We'd like to see a P50 under 300ms and a P95 as close to that as possible! Note, though, that this P50 number is as good as we've seen for any initial release of a new ASR model.
The model also supports speaker labels (diarization) and keyword biasing, has built-in endpointing, and can transcribe mixed-language speech.
Kudos to the Meta team. We love seeing new models that are strong performers in realtime voice agent pipelines.
Merin Mandanna retweeted
Pipecat v1.9.0 is out today, with support for @AIatMeta's new Muse Voice Transcribe model.
Muse Voice Transcribe is a streaming speech-to-text model. It has the best (lowest) semantic word error rate of any model we've tested.
We maintain a public, open source test suite called the Pipecat STT benchmark. This benchmark measures how well an STT model performs in a voice agent pipeline. We calculate a "semantic word error rate" across 1,000 speech input fragments. Semantic WER ignores small differences in transcription that don't impact an LLM's understanding of user speech, and in our experience is a better proxy for STT model accuracy than the simpler WER algorithms used in most speech recognition benchmarks.
The other critical metric for a voice agent is latency. We measure latency as "time to final segment" of the transcription. You can think of this as how long it takes for the STT model to deliver a complete text transcription after the user finishes speaking. Muse Voice Transcribe's TTFS is very good, though its long tail TTFS is a bit higher than we'd like to see. (The Meta team says they are optimizing for natural, model-driven endpointing, which certainly makes sense.) The P50 TTFS is 392 milliseconds and the P95 is 1,292 milliseconds. We'd like to see a P50 under 300ms and a P95 as close to that as possible! Note, though, that this P50 number is as good as we've seen for any initial release of a new ASR model.
The model also supports speaker labels (diarization) and keyword biasing, has built-in endpointing, and can transcribe mixed-language speech.
Kudos to the Meta team. We love seeing new models that are strong performers in realtime voice agent pipelines.
@NetflixIndia you know why we're asking, but you're aware today is the 10th, right? It's the 10th of September and it's past 7pm. 🥹
Merin Mandanna retweeted
Introducing Muse, the personal agent that understands your goals and works 24/7 to get things done for you.
Merin Mandanna retweeted
Meta has released Muse Voice Transcribe, taking the #1 spot for Final Transcript accuracy on AA-WER Streaming with 3.1% WER at 0.16s after end of speech
Muse Voice Transcribe is the first streaming Speech to Text model developed by Meta Superintelligence Labs. Meta states that the model was trained on more than 70 languages, with 25 extensively verified, and supports audio inputs exceeding one hour without required post-processing. It processes audio in 80ms chunks and is available through the Meta Model API, Meta AI for Mac and Muse Code.
Key takeaways
➤ Final Transcript: Muse Voice Transcribe achieves 3.1% WER at 0.16s after end of speech. It is more accurate and faster than Cartesia Ink-2 (semantic endpoints) at 3.4% and 0.43s, and more accurate but slower than Cartesia Ink-2 (external endpoints) at 4.0% and 0.07s. It is also more accurate, though slightly slower, than ElevenLabs Scribe v2 Realtime at 3.6% and 0.14s.
➤ First Partial Transcript: The model achieves 3.6% WER at 0.13s, just ahead of ElevenLabs Scribe v2 Realtime on accuracy and latency. It is more accurate and faster than Cartesia Ink-2 (semantic endpoints) at 4.9% and 0.17s, and more accurate but slower than Cartesia Ink-2 (external endpoints) at 4.0% and 0.07s.
➤ Price: Muse Voice Transcribe costs $0.18 per hour, or $3 per 1,000 minutes. This is below Cartesia Ink-2 at $4 and less than half the $6.50 charged for ElevenLabs Scribe v2 Realtime and Deepgram Flux.
See more details below ⬇️
Merin Mandanna retweeted
1/ today we're rolling out muse voice transcribe, our first real-time audio perception model - SOTA in streaming speech-to-text. also handles speaker diarization and endpointing natively in a single model.
Merin Mandanna retweeted
Muse Voice Transcribe is MSL's first real-time audio perception model -- rolling out today. SOTA in streaming speech-to-text, it handles speaker diarization, and endpointing natively in a single model.
Merin Mandanna retweeted
Muse Image is now available on Meta Model API and priced for production volumes at $0.01/image.
It’s an agentic image model that reasons before it renders. Each call searches the web to refine the output through iterative passes and evaluates the prompt for precise elements like charts and QR codes.
Text-to-image, single-image and multi-image editing, and multi-reference composition all live in one model, so there's no multi-step pipeline to stitch together.
Start building → bit.ly/4gsPeOV