DevRel @Speechmatics. I build voice agents and speech demos for real-world audio. Code, AI, benchmarks, and the occasional talking game. Start building below.
London, England
Joined October 2012
- Tweets188
- Following270
- Followers166
- Likes124
My favourite part of a live voice AI demo is handing someone the mic and seeing what they try. You KNOW someone鈥檚 going to try to break it. 馃槀
Heading to #VapiCon? Put our demos through their paces at Booth 14. The @Speechmatics team is bringing live transcription, our Speaker ID Voice Agent and Agent STT turn-taking demos.
Bring your awkward questions. Tell us what you鈥檙e building. I want to hear about the weird experiments too. 馃敟
馃搷 Fort Mason, San Francisco. 11 and 12 November.
Use SPEECHMATICS20 at checkout: vapicon.ai/
Who鈥檚 going? #VoiceAI
After a week with @livekit @fin_ai , @aquavoice ,@livekit, @cartesia , @AgoraIO, @Vapi_AI and many other builders across SF, one thing is clear:
Voice AI has moved past can it talk?
The real question is whether it understands well enough to act.
Try @Speechmatics. Stress it. Break it. Show us what you build.
Here is my summary below 馃憞
#SFTechWeek #VoiceAI
@Speechmatics vs the Golden Gate Bridge vs F-15s
One laptop.
Built-in mic.
No cleanup.
Wind, traffic, crowds, jets overhead.
I ran live transcription anyway.
Because STT doesnt just need to work in a quiet room.
It needs to get names, instructions and numbers right when the real world is doing everything it can to break it.
That鈥檚 the test.
#Speechmatics #VoiceAI #SpeechToText #SFTechWeek
The more powerful voice agents become, the less room there is for close enough.
Great session tonight at #SFTechWeek with @aquavoice , @livekit and @Speechmatics .
The demos were fun, but the bigger point was serious:
If a voice agent can change your calendar, update systems, or cancel a flight, one bad transcription can have real consequences.
That is why accuracy, context, turn-taking and diarization matter just as much as latency.
Voice is becoming an interface.
Now it has to become one we can trust.
If voice becomes the default customer interface, speech-to-text stops being a feature.
It becomes infrastructure.
Great session from @rati_zv and @gavinjoyce at @fin_ai today.
The more capable voice agents become at taking real actions, the more important the first layer gets:
Did the agent actually understand the customer correctly?
That鈥檚 exactly the problem we鈥檙e focused on with Agent STT at @Speechmatics .
Accuracy, turn-taking, interruptions and latency suddenly matter a lot more when the AI can actually do something.
#VoiceAI #SFTechWeek #Speechmatics