ask-ai
Latency Spikes
Text to Speech
Getting a BAA with Deepgram for health AI application pilot
Speech to Text
Struggling to implement Flux with Voice Agent SDK
Nova Model
Elevated connection error incident
How many languages are currently supported by the Deepgram Voice Agent API?In the documentation, I
Blank Transcript problem
Blank Transcript problem
Flux multilingual support
Best way to continue to capture the user response during a conversation?
Explanation of Deepgram Voice Agent platform
Long
How to make the greeting message barge in proof?
Is there a way to use tuned gemini model (it was tuned on vertex ai) in the Deepgram voice assistant
Best way to end the call?
Long
How to specify output codec with Voice Agent?
Long
STT Nova 3 General support for Filler Words
Speech to Text
Error while configuring nova 3
Elevenlabs error
To implement barge in
How can I give my voice agent web_search access by tool calling?
AI Agents
STT nova-3 using language=multi doesn't work with french anymore
updated model links list
Speaker number
Nova-3 Streaming API returns 400 Bad Request with Tagalog (tl) language
Speech to Text
Deepgram Example for voice agent is not working
Long
404 voice agent
AI Agents
"PROVIDER_ERROR" while trying to run the starter node js app
AI Agents
Starter node js app for voice agent
Javascript v5 SDK can't npm start
Think and speak models with free tier?
The read operation timed out
How do i stop prerecorded speech from time out
Async
Long
Having lag issues on Native platforms
Unable to login to deepgram
How do generate a subtitle from pre-recoreded audio?
Freelancers Needed
Features
Text to Speech
AI Agents
Pricing
Speech to Text
Does Python SDK Voice Agent (AgentV1ListenProvider )not support flux-general-en?
AI Agents
Can't access acount.
Irregular speaker assignment
Speech to Text
Python deepgram-sdk 5.3.0 support for `detect_entities`
multi language transcription - English and Thai
Speech to Text
Getting english transcriptions in nova-3 spanish ("es") language STT model
Speech to Text
STT error while using nova-2-phonecall model over Web socket on telephony system
Speech to Text
STT low-volume input not getting picked-up by STT model
Speech to Text
How can I use my API key in Superwhisper for Mac?
Websocket for text to speech is not wroking
WebSocket streaming (v2/listen) failing with 1006 error - account limitation?
flux is not transcribing single word responses.
Speech to Text
Does using key term prompting with Flux streaming increase latency ?