ask-ai
Different transcripts in deepgram playground vs python sdk.
Migrating to temporary tokens
Converting transcript word timing to absolute clock time
Speech to Text
Hindi
Text to Speech
AI Agents
Speech to Text
Does Deepgram use user data for training?
stt not working with streamed pcm data: 4800 hz, 2 channels, 2 byte data.
Voice model for childeren
Text to Speech
Delay in transcription during a live conversation on a phone call.
Features
Long
Speech to Text
Difference between utterance_end_ms and utterances in STT
Long
Speech to Text
Issues with o transcribing as 0
websocket 1011 Live Streaming
Long
Slow in STT in number reading
Spanish TTS
Can I use nova-3 multi with 8000hz mulaw?
Capturing hmmm in conversations
API Key not Working
Do you provide close in stt sdk?
Speech to Text
Using alaw instead of mulaw
Strange pause when trying to convert TTS -- seems to happen at random times around ellipses
Issues with connection of Voice Agent API
Long
Voice Agent API: How to pass the language of the STT model?
Voice Agent API
MCP Server with Agent API
pending status for speak api
Speech to Text
Difference between aura2 and aura tts
Text to Speech
i am using the javascript sdk in deno and im still getting a cors error when using deepgram
Long
Deep guttural swamp creature sound during TTS
Issue with Character Limit in Text-to-Speech
Agent API on premise
Need optimize settings for transcribing call
Speech to Text
affiliate marketing
Features
Speech to Text
Can I use speed in tts api?
Text to Speech
Is it possible for deepgram to diarize multiple (3+) speakers? If so, how accurate is it?
Availability of system cutting tts when user speaks while tts is coming out
Long
Speech to Text
does puting silence in live transcript increase error or enhance performance
can you confirm if aura 2.0 has websocket
Text to Speech
Front end transcription display Issue
Speech-to-text transcription isn't displaying in the web UI
Text to Speech
Long
AI Agents
Speech to Text
Missing "model-uuid" prop when using new aura-2 voice in python sdk
TTS interruption on on_speech_started
Text to Speech
Speech to Text
Nova-3 in french
Speech to Text
Where to clear TTS audio buffer
Bringing my own LLM
Getting code 1011 errors using Python on a LiveTranscription
Nextjs Proxy
lesser value for utterence_end_ms throwing an error
Speech to Text
Call time limitation for pay as you go
Speech to Text
STT Transcription Latency
Numerals with Nova-3 Multilingual
Speech to Text
Agent think latency