ask-ai

Flux websocket closure issues 6 messages

Nov 13, 2025, 10:54 AM Speech to Text

Troubleshooting transcription frames 10 messages

Nov 12, 2025, 5:47 AM Speech to Text

Minimum audio duration required for Speaker Diarization? 9 messages

Nov 11, 2025, 5:29 AM

Speaker Diarization not working for merged raw PCM audio (all detected as Speaker 0) 9 messages

Nov 11, 2025, 4:50 AM

Utterance Split Triggering Below Configured 3s Threshold in Nova 3 (German Audio) 5 messages

Nov 10, 2025, 1:51 PM

Status 403 5 messages

Nov 10, 2025, 5:54 AM Speech to Text

stream api connection close after 4 min 4 messages

Nov 9, 2025, 6:25 AM

Too many keys created 3 messages

Nov 7, 2025, 3:03 PM

I need to understand how deepgram work 13 messages

Nov 6, 2025, 5:06 AM

Deepgram not outputting any transcription some times via phone call 9 messages

Nov 5, 2025, 7:11 AM

Hi there, i keep getting error 1006 no matter what i do. What am i doing wrong? 12 messages

Nov 4, 2025, 9:54 PM

I want to use my eleven labs with deepgram voiceagent, the setup doesn't return error no audio 6 messages

Nov 4, 2025, 9:25 PM

What languages does voice agent language support? 20 messages

Nov 4, 2025, 4:20 PM

Python SDK 5 only supports En and Es voice agent language? 4 messages

Nov 2, 2025, 11:09 PM Text to Speech AI Agents Speech to Text

Billing details 7 messages

Oct 31, 2025, 2:57 PM

Kuberentes pod termination behavior 12 messages

Oct 29, 2025, 6:07 PM

Python sdk version 5 voice agent 13 messages

Oct 28, 2025, 3:47 PM

Streaming STT VAD 4 messages

Oct 28, 2025, 1:35 PM

invoices 15 messages

Oct 23, 2025, 9:33 AM

Deepgram Flux not transcribing "PPF" acronym in real-time streaming 4 messages

Oct 23, 2025, 12:22 AM Speech to Text

Streaming STT VAD 4 messages

Oct 22, 2025, 5:51 PM

My function call is waiting for user turn when it should not 10 messages

Oct 22, 2025, 7:36 AM

TTS with Timestamps 9 messages

Oct 20, 2025, 3:04 PM Text to Speech

Word start not present in Flux 4 messages

Oct 20, 2025, 1:28 PM

python sdk 5 3 messages

Oct 20, 2025, 12:54 PM

no output config for voice agent python sdk 3 messages

Oct 20, 2025, 12:43 AM

Dropped STT for Resumed media recorder 15 messages

Oct 16, 2025, 2:12 PM

No credits on signup 3 messages

Oct 15, 2025, 3:44 AM

Audio diarization 5 messages

Oct 14, 2025, 9:22 PM

Multilanguage support 6 messages

Oct 14, 2025, 12:20 PM

Voice Agent Configuration 71 messages

Oct 12, 2025, 9:39 AM Long

connection.start_listening() hangs for realtime transcription 5 messages

Oct 12, 2025, 2:13 AM

I am getting transcription as Empty 5 messages

Oct 9, 2025, 12:24 PM Speech to Text

Voice agent noise cancellation 5 messages

Oct 9, 2025, 12:18 PM

Deepgram sdk v5 questions 4 messages

Oct 8, 2025, 4:11 PM

cost via API 9 messages

Oct 8, 2025, 3:17 PM

Getting frequent http 402 status today 5 messages

Oct 7, 2025, 3:21 PM

flux audio_window_start is always 0 at the first non empty transcript 7 messages

Oct 6, 2025, 2:24 PM

Does Deepgram offer Hindi, Arabic, or Serbian? 4 messages

Oct 3, 2025, 11:24 PM Text to Speech Speech to Text

Voice agent: STT not matching with TTs 3 messages

Oct 3, 2025, 7:27 PM

best stt? 13 messages

Oct 3, 2025, 6:02 PM

Does deepgram Flux work for pre-recorded audio? 4 messages

Oct 3, 2025, 1:48 PM Features Speech to Text

Filtering accuracy 13 messages

Oct 2, 2025, 7:09 PM

Calling customers and storing responses, even when they called back to same number 5 messages

Oct 1, 2025, 7:40 PM Speech to Text

Access recording and transcript when integrating with Twilio 13 messages

Oct 1, 2025, 7:24 AM AI Agents

Turkish language problem nova-3 multi 5 messages

Sep 30, 2025, 5:10 PM

Deepgram not able to process when I switch the audio buffer 6 messages

Sep 30, 2025, 10:33 AM

Punctuate not supported in streaming chinese audio 4 messages

Sep 29, 2025, 5:31 PM Speech to Text

Eleven Labs TTS config 18 messages

Sep 29, 2025, 10:17 AM

Deepgram STT only works with English Audio in my pipecat voice agent 5 messages

Sep 29, 2025, 12:18 AM