# \#python **URL:** https://community.livekit.io/tag/python/15.md [Latest](https://community.livekit.io/latest.md) · [Categories](https://community.livekit.io/categories.md) · [Tags](https://community.livekit.io/tags.md) --- ## [Empty\_timeout and ceiling of plans](https://community.livekit.io/t/empty-timeout-and-ceiling-of-plans/2337)
**Author:** [@Aleksandr\_Beliaev](https://community.livekit.io/u/Aleksandr_Beliaev)\ **Replies:** 0\ **Last updated:** [October 22, 2026, 7:27pm UTC](https://community.livekit.io/t/empty-timeout-and-ceiling-of-plans/2337 "2026-10-22T19:27:42Z")
Hi, Hello LiveKit Team and Community! I’d like to ask two questions about a self-hosted Python agent (livekit-agents 1.8.8) connecting to LiveKit Cloud as a participant: Is a room billed while it has no participants … --- ## [Looking for a Realtime Voice AI Engineer / Consultant — LiveKit, Vapi, Retell + Stateful Backend](https://community.livekit.io/t/looking-for-a-realtime-voice-ai-engineer-consultant-livekit-vapi-retell-stateful-backend/2304)
**Author:** [@alex3](https://community.livekit.io/u/alex3)\ **Replies:** 4\ **Last updated:** [October 20, 2026, 5:24pm UTC](https://community.livekit.io/t/looking-for-a-realtime-voice-ai-engineer-consultant-livekit-vapi-retell-stateful-backend/2304 "2026-10-20T17:24:17Z")
I’m looking for an experienced realtime voice engineer for a paid architecture/code review of an existing AI receptionist. We originally built the voice runtime on LiveKit Agents. The business side of the system is alre… --- ## [Turn-taking on real SIP calls: what cut my median reply from 2.44 s to 1.81 s (plus a question on short answers)](https://community.livekit.io/t/turn-taking-on-real-sip-calls-what-cut-my-median-reply-from-2-44-s-to-1-81-s-plus-a-question-on-short-answers/2139)
**Author:** [@Mohammed\_Usmani](https://community.livekit.io/u/Mohammed_Usmani)\ **Replies:** 2\ **Last updated:** [September 29, 2026, 2:56pm UTC](https://community.livekit.io/t/turn-taking-on-real-sip-calls-what-cut-my-median-reply-from-2-44-s-to-1-81-s-plus-a-question-on-short-answers/2139 "2026-09-29T14:56:11Z")
I’ve been measuring a LiveKit Agents phone agent (Python, SIP, Deepgram, Gemini, Cartesia) turn by turn, and wanted to share a few findings in case they help others, plus one open question. What moved the numbers (agent… --- ## [Gemini Realtime API error: 1007 None. The audio content type (CONTENT\_TYPE\_AUDIO) is not supported for this model](https://community.livekit.io/t/gemini-realtime-api-error-1007-none-the-audio-content-type-content-type-audio-is-not-supported-for-this-model/1908)
**Author:** [@Peace](https://community.livekit.io/u/Peace)\ **Replies:** 6\ **Last updated:** [September 18, 2026, 10:13am UTC](https://community.livekit.io/t/gemini-realtime-api-error-1007-none-the-audio-content-type-content-type-audio-is-not-supported-for-this-model/1908 "2026-09-18T10:13:59Z")
1. Error Hi, I had reported this exact same error a while back (Kindly view here)and since then it was working temporarily 2. Context My observations remain same that I am still not able to figure out when and due to w… --- ## [LiveKit Plugin for Smart Turn EOT Detection Models](https://community.livekit.io/t/livekit-plugin-for-smart-turn-eot-detection-models/2013)
**Author:** [@Santhosh](https://community.livekit.io/u/Santhosh)\ **Replies:** 5\ **Last updated:** [September 8, 2026, 3:34pm UTC](https://community.livekit.io/t/livekit-plugin-for-smart-turn-eot-detection-models/2013 "2026-09-08T15:34:34Z")
Hey everyone! :waving\_hand: I wanted to use smart-turn model for my language in a LiveKit agents. Found out there wasn’t any straightforward way to plug a Smart Turn model directly into LiveKit, so I ended up building i… --- ## [Bluetooth issue](https://community.livekit.io/t/bluetooth-issue/1935)
**Author:** [@Dwain\_ABRIVARD](https://community.livekit.io/u/Dwain_ABRIVARD)\ **Replies:** 4\ **Last updated:** [September 8, 2026, 12:59pm UTC](https://community.livekit.io/t/bluetooth-issue/1935 "2026-09-08T12:59:44Z")
When I start a LiveKit session, Bluetooth automatically disconnects on the tablet. I have a Kotlin app and a website, and Bluetooth does not work on tablets with either of them. --- ## [Images disabled for Gemma via LiveKit Inference](https://community.livekit.io/t/images-disabled-for-gemma-via-livekit-inference/1997)
**Author:** [@Muhammad\_Khalid](https://community.livekit.io/u/Muhammad_Khalid)\ **Replies:** 4\ **Last updated:** [September 7, 2026, 9:55am UTC](https://community.livekit.io/t/images-disabled-for-gemma-via-livekit-inference/1997 "2026-09-07T09:55:05Z")
Hi there! We’ve been using Gemma via LiveKit Inference in production since August 24th around 5pm PDT. Before deploying the Gemma-powered agent to production we tested it internally including uploading images which Gemma… --- ## [LiveKit Inference STT — HTTP 429 on First Clean Connection](https://community.livekit.io/t/livekit-inference-stt-http-429-on-first-clean-connection/1967)
**Author:** [@Brainz\_Dimilo](https://community.livekit.io/u/Brainz_Dimilo)\ **Replies:** 2\ **Last updated:** [September 1, 2026, 1:43pm UTC](https://community.livekit.io/t/livekit-inference-stt-http-429-on-first-clean-connection/1967 "2026-09-01T13:43:20Z")
Hi LiveKit Support, I’m experiencing a persistent HTTP 429 Too Many Requests error when attempting to use LiveKit Inference STT with: deepgram/nova-3 We performed a controlled clean-state test to rule out application-… --- ## [How can I sendText from human participant to agent participant](https://community.livekit.io/t/how-can-i-sendtext-from-human-participant-to-agent-participant/1933)
**Author:** [@Kamal\_Moha](https://community.livekit.io/u/Kamal_Moha)\ **Replies:** 2\ **Last updated:** [August 26, 2026, 6:20pm UTC](https://community.livekit.io/t/how-can-i-sendtext-from-human-participant-to-agent-participant/1933 "2026-08-26T18:20:57Z")
I’m using Whatsapp Connector so that whenever a user sends a message during the call, I want that message the user sent via whatsapp chat to be sent to the agent using sendText ( Sending text | LiveKit Documentation ). T… --- ## [Is there any way to recover my LiveKit project/code from LiveKit infrastructure?](https://community.livekit.io/t/is-there-any-way-to-recover-my-livekit-project-code-from-livekit-infrastructure/1931)
**Author:** [@Abderahim\_Mazouz](https://community.livekit.io/u/Abderahim_Mazouz)\ **Replies:** 1\ **Last updated:** [August 25, 2026, 7:20pm UTC](https://community.livekit.io/t/is-there-any-way-to-recover-my-livekit-project-code-from-livekit-infrastructure/1931 "2026-08-25T19:20:35Z")
Hi everyone, I recently lost my laptop, and unfortunately I lost the local codebases of two projects I was working on with LiveKit. The problem is that I don’t have a copy of the source code on GitHub, GitLab, or any o… --- ## [LiveKit OpenAI Plugin with DeepInfra Backend: API Returns Usage Logs but No Audio Output](https://community.livekit.io/t/livekit-openai-plugin-with-deepinfra-backend-api-returns-usage-logs-but-no-audio-output/1883)
**Author:** [@Kerem\_Kezer](https://community.livekit.io/u/Kerem_Kezer)\ **Replies:** 4\ **Last updated:** [August 21, 2026, 12:51pm UTC](https://community.livekit.io/t/livekit-openai-plugin-with-deepinfra-backend-api-returns-usage-logs-but-no-audio-output/1883 "2026-08-21T12:51:46Z")
When using the livekit-plugins-openai TTS class configured with a custom base\_url to route requests to DeepInfra’s OpenAI-compatible endpoint, the API successfully processes the request and logs show usage/successful res… --- ## [Openai TTS sends stream\_format="sse" to every non-OpenAI backend, so compatible endpoints return audio that gets thrown away](https://community.livekit.io/t/openai-tts-sends-stream-format-sse-to-every-non-openai-backend-so-compatible-endpoints-return-audio-that-gets-thrown-away/1892)
**Author:** [@abidullahcs.uk](https://community.livekit.io/u/abidullahcs.uk)\ **Replies:** 4\ **Last updated:** [August 21, 2026, 9:03am UTC](https://community.livekit.io/t/openai-tts-sends-stream-format-sse-to-every-non-openai-backend-so-compatible-endpoints-return-audio-that-gets-thrown-away/1892 "2026-08-21T09:03:33Z")
Hi team, I think there’s a bug in the OpenAI TTS plugin that breaks any OpenAI-compatible backend. Two people have hit it on the forum without anyone finding the cause, so I dug into it. The plugin decides how to read … --- ## [Voice feeling very robotic and less expressive](https://community.livekit.io/t/voice-feeling-very-robotic-and-less-expressive/1793)
**Author:** [@Tanish\_Rajput](https://community.livekit.io/u/Tanish_Rajput)\ **Replies:** 3\ **Last updated:** [August 7, 2026, 7:34pm UTC](https://community.livekit.io/t/voice-feeling-very-robotic-and-less-expressive/1793 "2026-08-07T19:34:08Z")
Hi I am building a telephony outbound voice agent, and I am using sarvam’s STT and TTS models but the voice is feeling very robotic and without expressions. It’s like I am talking to a machine and also I want to make it… --- ## [Gemini-3.1-flash-tts-preview](https://community.livekit.io/t/gemini-3-1-flash-tts-preview/1797)
**Author:** [@Pete](https://community.livekit.io/u/Pete)\ **Replies:** 3\ **Last updated:** [August 4, 2026, 7:47am UTC](https://community.livekit.io/t/gemini-3-1-flash-tts-preview/1797 "2026-08-04T07:47:46Z")
Team, when I look at Gemini plugin TTS docs livekit.plugins.google API documentation I see a lot of tuning options. However, I am not sure that Gemini 3.1 TTS supports any of them (Gemini-TTS | Cloud Text-to-Speech | … --- ## [New Cloud Agent versions crashloop in eu-central](https://community.livekit.io/t/new-cloud-agent-versions-crashloop-in-eu-central/1791)
**Author:** [@kevin.nguyen](https://community.livekit.io/u/kevin.nguyen)\ **Replies:** 3\ **Last updated:** [August 3, 2026, 4:03pm UTC](https://community.livekit.io/t/new-cloud-agent-versions-crashloop-in-eu-central/1791 "2026-08-03T16:03:59Z")
Newly created Cloud Agent versions in eu-central are entering CrashLoopBackOff shortly after startup. We first saw this in development on July 29, 2026, and again in staging and production on August 2. A retained version… --- ## [Subject: Registered worker never receives jobs (Phone Number & Manual Room) – Free Tier Limitation?](https://community.livekit.io/t/subject-registered-worker-never-receives-jobs-phone-number-manual-room-free-tier-limitation/1773)
**Author:** [@David\_Maxa](https://community.livekit.io/u/David_Maxa)\ **Replies:** 1\ **Last updated:** [July 31, 2026, 9:29am UTC](https://community.livekit.io/t/subject-registered-worker-never-receives-jobs-phone-number-manual-room-free-tier-limitation/1773 "2026-07-31T09:29:30Z")
I am building a Voice AI Receptionist using the LiveKit Agents framework (Python). My agent successfully registers with LiveKit Cloud, but it never receives any jobs—not from incoming phone calls, and not even from manua… --- ## [api.CreateSIPParticipantRequest is not giving 'media' param option](https://community.livekit.io/t/api-createsipparticipantrequest-is-not-giving-media-param-option/1762)
**Author:** [@siddharthmot](https://community.livekit.io/u/siddharthmot)\ **Replies:** 4\ **Last updated:** [July 31, 2026, 3:37am UTC](https://community.livekit.io/t/api-createsipparticipantrequest-is-not-giving-media-param-option/1762 "2026-07-31T03:37:17Z")
As per documentation : SIP APIs | LiveKit Documentation It should accept media param, but livekit 1.5 is not suggesting it. I want to use media\_timeout , as for call hold the call is getting hang up after 15 seconds. W… --- ## [Gemini Realtime API error: 1007 None. The audio content type (CONTENT\_TYPE\_AUDIO) is not supported for this model configuration](https://community.livekit.io/t/gemini-realtime-api-error-1007-none-the-audio-content-type-content-type-audio-is-not-supported-for-this-model-configuration/1737)
**Author:** [@Peace](https://community.livekit.io/u/Peace)\ **Replies:** 3\ **Last updated:** [July 27, 2026, 10:47pm UTC](https://community.livekit.io/t/gemini-realtime-api-error-1007-none-the-audio-content-type-content-type-audio-is-not-supported-for-this-model-configuration/1737 "2026-07-27T22:47:06Z")
1. Error Receiving 1007 error from Gemini Live API 2. System Windows 11 3. Context The only model I am using is → REALTIME\_MODEL = “gemini-2.5-flash-native-audio-preview-12-2025” Crash occurrence is complicated becaus… --- ## [AWS Nova Sonic RealtimeModel (amazon.nova-2-sonic-v1:0): metrics emitted repeatedly and ttftalways0.0](https://community.livekit.io/t/aws-nova-sonic-realtimemodel-amazon-nova-2-sonic-v1-0-metrics-emitted-repeatedly-and-ttftalways0-0/1665)
**Author:** [@Shivakant\_Yadav](https://community.livekit.io/u/Shivakant_Yadav)\ **Replies:** 2\ **Last updated:** [July 21, 2026, 12:34am UTC](https://community.livekit.io/t/aws-nova-sonic-realtimemodel-amazon-nova-2-sonic-v1-0-metrics-emitted-repeatedly-and-ttftalways0-0/1665 "2026-07-21T00:34:32Z")
@livekit Hi Livekit team, When using the AWS Nova Sonic realtime model (amazon.nova-2-sonic-v1:0) via the livekit-plugins-aws realtime integration, I’m seeing two problems with the RealtimeModel metrics events: Metri… --- ## [Inbound SIP calls connected but agent produced no audio for ~1 hour (US East / Ashburn) — anyone else on July 18 ~02:45 UTC?](https://community.livekit.io/t/inbound-sip-calls-connected-but-agent-produced-no-audio-for-1-hour-us-east-ashburn-anyone-else-on-july-18-02-45-utc/1674)
**Author:** [@Basel\_Hussain](https://community.livekit.io/u/Basel_Hussain)\ **Replies:** 1\ **Last updated:** [July 20, 2026, 9:19am UTC](https://community.livekit.io/t/inbound-sip-calls-connected-but-agent-produced-no-audio-for-1-hour-us-east-ashburn-anyone-else-on-july-18-02-45-utc/1674 "2026-07-20T09:19:28Z")
We run a production voice agent on LiveKit Cloud (Ship plan, US East / oashburn1b, livekit-agents 1.6.2, Python, inbound via Twilio Elastic SIP trunk). On July 18 between roughly 02:44 and 02:45 UTC, three consecutive i… --- ## [Open-source latency waterfall for voice agents — how are you profiling per-turn latency?](https://community.livekit.io/t/open-source-latency-waterfall-for-voice-agents-how-are-you-profiling-per-turn-latency/1584)
**Author:** [@haohui\_yang](https://community.livekit.io/u/haohui_yang)\ **Replies:** 6\ **Last updated:** [July 13, 2026, 3:06am UTC](https://community.livekit.io/t/open-source-latency-waterfall-for-voice-agents-how-are-you-profiling-per-turn-latency/1584 "2026-07-13T03:06:22Z")
Built a small open-source latency waterfall for voice agents — it records user-stop → STT final → LLM first token → TTS first byte → playback (plus each tool/function call as its own timeline segment) and renders a per-t… --- ## [Tool calling with non-GPT OpenAI models on LiveKit agents (Gemma, Nemotron etc.) not working](https://community.livekit.io/t/tool-calling-with-non-gpt-openai-models-on-livekit-agents-gemma-nemotron-etc-not-working/1555)
**Author:** [@vvgr001](https://community.livekit.io/u/vvgr001)\ **Replies:** 5\ **Last updated:** [July 7, 2026, 2:25pm UTC](https://community.livekit.io/t/tool-calling-with-non-gpt-openai-models-on-livekit-agents-gemma-nemotron-etc-not-working/1555 "2026-07-07T14:25:10Z")
Hi, We are using GPT 4.1 and later OpenAI models (including the OSS models) the most as those seem to have the most accurate tool calling capabilities. Somehow; within LiveKit agents, it seems like no other capable mod… --- ## [Terrible times with vapi + dialpads. Is livekit going to be any better](https://community.livekit.io/t/terrible-times-with-vapi-dialpads-is-livekit-going-to-be-any-better/1552)
**Author:** [@Preesha\_Gehlot](https://community.livekit.io/u/Preesha_Gehlot)\ **Replies:** 1\ **Last updated:** [July 6, 2026, 11:57am UTC](https://community.livekit.io/t/terrible-times-with-vapi-dialpads-is-livekit-going-to-be-any-better/1552 "2026-07-06T11:57:36Z")
We want to build outbound voice agents (using number A) that can handle dialpads on numbers they call, reach an operator and ask a query. But testing these agents that have dialpad tools has been notoriously hard on vap… --- ## [Generate reply timeout for gemini-live-2.5-flash-native-audio realtime model](https://community.livekit.io/t/generate-reply-timeout-for-gemini-live-2-5-flash-native-audio-realtime-model/1505)
**Author:** [@Harshita\_Sukumar\_Patil](https://community.livekit.io/u/Harshita_Sukumar_Patil)\ **Replies:** 2\ **Last updated:** [June 28, 2026, 1:38am UTC](https://community.livekit.io/t/generate-reply-timeout-for-gemini-live-2-5-flash-native-audio-realtime-model/1505 "2026-06-28T01:38:45Z")
@livekit @LiveKit-Community @livekitteams @darryncampbell @CWilson @Muhammad\_Usman\_Bashir Hi LiveKit Team, We are experiencing intermittent timeouts while using the Gemini Live 2.5 Flash Native Audio realtime model via… --- ## [Audio Intelligence for Voice Agents](https://community.livekit.io/t/audio-intelligence-for-voice-agents/1457)
**Author:** [@Pawel\_Lach](https://community.livekit.io/u/Pawel_Lach)\ **Replies:** 1\ **Last updated:** [June 19, 2026, 7:44am UTC](https://community.livekit.io/t/audio-intelligence-for-voice-agents/1457 "2026-06-19T07:44:15Z")
While most STT engines can only transcribe speech to text, they are unable to hear or recognize anything else. That’s why we developed Tyto: to bring audio intelligence to Voice AI and give your agent context about the a… --- ## [Session.say() hangs indefinitely (~20s+) when using Gemini RealtimeModel(gemini 3.1) as llm together with google.beta.GeminiTTS as tts; session.input.set\_audio\_enabled() / aec\_warmup\_duration do not reliably block user interruption in this configuration](https://community.livekit.io/t/session-say-hangs-indefinitely-20s-when-using-gemini-realtimemodel-gemini-3-1-as-llm-together-with-google-beta-geminitts-as-tts-session-input-set-audio-enabled-aec-warmup-duration-do-not-reliably-block-user-interruption-in-this-configuration/1448)
**Author:** [@Jayesh\_Shinde](https://community.livekit.io/u/Jayesh_Shinde)\ **Replies:** 3\ **Last updated:** [June 18, 2026, 10:03am UTC](https://community.livekit.io/t/session-say-hangs-indefinitely-20s-when-using-gemini-realtimemodel-gemini-3-1-as-llm-together-with-google-beta-geminitts-as-tts-session-input-set-audio-enabled-aec-warmup-duration-do-not-reliably-block-user-interruption-in-this-configuration/1448 "2026-06-18T10:03:41Z")
Summary When using llm=google.beta.realtime.RealtimeModel (gemini-3.1-flash-live-preview) together with a separate tts=google.beta.GeminiTTS(gemini-3.1-flash-tts-preview) instance on the same AgentSession, a sequence of … --- ## [Incorrect/false high e2e Latency \> 203 seconds OR sometimes not present at all in chat item](https://community.livekit.io/t/incorrect-false-high-e2e-latency-203-seconds-or-sometimes-not-present-at-all-in-chat-item/1425)
**Author:** [@Kaushal\_Shah](https://community.livekit.io/u/Kaushal_Shah)\ **Replies:** 5\ **Last updated:** [June 17, 2026, 7:44am UTC](https://community.livekit.io/t/incorrect-false-high-e2e-latency-203-seconds-or-sometimes-not-present-at-all-in-chat-item/1425 "2026-06-17T07:44:29Z")
We’ve noticed that for some rooms the reported E2E latency is either extremely high (often \>200 seconds) or missing entirely. From reviewing the session recordings, there does not appear to be any actual user-visible de… --- ## [Reliable Agent Room Join Issue – Dispatched Agents Not Joining Room Despite Successful Request](https://community.livekit.io/t/reliable-agent-room-join-issue-dispatched-agents-not-joining-room-despite-successful-request/1433)
**Author:** [@moonlight.homestaydalat](https://community.livekit.io/u/moonlight.homestaydalat)\ **Replies:** 1\ **Last updated:** [June 15, 2026, 9:47am UTC](https://community.livekit.io/t/reliable-agent-room-join-issue-dispatched-agents-not-joining-room-despite-successful-request/1433 "2026-06-15T09:47:18Z")
We are experiencing a reliability issue with LiveKit Agents on your Cloud platform. Our Setup: We deploy multiple Python-based agents (single process, one agent per dispatch) into the same room. Each agent is assigned… --- ## [Upgrading python livekit-agents to 1.5.6 causing memory issues](https://community.livekit.io/t/upgrading-python-livekit-agents-to-1-5-6-causing-memory-issues/976)
**Author:** [@nilkanth](https://community.livekit.io/u/nilkanth)\ **Replies:** 18\ **Last updated:** [June 12, 2026, 6:35am UTC](https://community.livekit.io/t/upgrading-python-livekit-agents-to-1-5-6-causing-memory-issues/976 "2026-06-12T06:35:10Z")
Hello, We have recently upgraded python livekit-agents from 1.5.1 to 1.5.6, and it caused massive spikes in memory. Here is the AWS graph before and after deployment. NOTE: The sudden drop in memory usage is due to aut… --- ## [Livekit API Error](https://community.livekit.io/t/livekit-api-error/1397)
**Author:** [@siddharthmot](https://community.livekit.io/u/siddharthmot)\ **Replies:** 2\ **Last updated:** [June 11, 2026, 4:37am UTC](https://community.livekit.io/t/livekit-api-error/1397 "2026-06-11T04:37:54Z")
Don’t know why, but getting this errors for multiple calls. The call goes well but at the end the error is getting triggered : livekit\_api::signal\_client::signal\_stream:371:livekit\_api::signal\_client::signal\_stream - … [Next page](https://community.livekit.io/tag/python/15.md?match_all_tags=true&page=1&tags%5B%5D=python)