A stuck connection fails fast now, and the bot keeps talking

Pipecat 1.14.0 is mostly about connections that used to hang. A peer that stops reading or a session that drops mid-sentence could stall a bot. Now they fail fast, keep what the user said, and recover. There are new services too, and a short list of things to do before you upgrade.

Slide text

Release · v1.14.0

Pipecat 1.14.0

A stuck connection fails fast now, and the bot keeps talking

Transport websocket sends
Daily callbacks

STT Deepgram Flux
Cartesia · Sarvam

LLM Perplexity · Omni
Smallest

TTS Rime · Deepgram
Inworld

When a websocket peer stopped reading, a send could wait many minutes for TCP to give up while the whole pipeline behind it waited. Now each send is bounded at 5 seconds. One that runs over drops the connection, and the normal reconnect takes over. A send timeout setting on the websocket service changes the bound, and None turns it off.

Slide text

Fixed · WebsocketService

A websocket send now gives up after 5 seconds

Before

Waits on a full write buffer until TCP gives up: many minutes, with every processor after it stuck

1.14.0

Drops the connection, raises ConnectionClosedError, and the service reconnects

Change the bound with ws_send_timeout on WebsocketService, or set it to None

Deepgram Flux, Cartesia Turns, and Sarvam Realtime share a set of fixes. If the connection ends partway through a turn, the turn now ends with the transcript received so far. Flux and Cartesia Turns reconnect in the background, so audio keeps moving. A connection that opens but is never confirmed is retried, and the service gives up after three in a row. A rejected setting names the provider's reason.

Slide text

Fixed · streaming STT

When the connection drops mid-turn, speech-to-text keeps what the user said

	Deepgram Flux	Cartesia Turns	Sarvam Realtime
Ends the turn with the transcript so far	✓	✓	✓
Reconnects in the background	✓	✓	–
Retries an unconfirmed connection, gives up after 3	✓	✓	✓
Rejected settings name the provider's reason	✓	✓	✓

The LLM text processor now takes text transforms. In the updated example, one strips emoji right after the LLM. Because it runs before the text splits toward the voice, the context, and the client, the LLM never sees its own emoji, and stops adding more.

Slide text

Added · LLMTextProcessor

One text transform now rewrites what the bot says, remembers and shows

LLM

LLMTextProcessor text_transforms

TTS the voice

Context what the LLM sees next turn

Client the app

llm_text_processor = LLMTextProcessor(text_transforms=[("*", strip_emoji)])

A new Perplexity service uses its Agent API, which answers with web search and supports function calling. NVIDIA's Nemotron Omni hears the user directly, so in audio mode it replaces your speech-to-text. Zoom Scribe Live gets a streaming speech-to-text service. And Smallest AI's Electron model connects through its OpenAI-compatible Waves API.

Slide text

Added · services

Perplexity's Agent API, Nemotron Omni, Zoom Scribe and Electron plug in

Perplexity Agent PerplexityAgentHttpLLMService

Answers with web search, supports function calling

NVIDIA Nemotron Omni NvidiaOmniLLMService

Hears the user directly and replaces the STT service

Zoom Scribe Live ZoomAISTTService

Streaming speech-to-text, pipecat-ai[zoom-ai]

Smallest Electron SmallestLLMService

OpenAI-compatible Waves API; pipecat init offers it

This is the change you have to make. RimeV1TTSService now requires a model in its settings. Set coda or mistv3, and the service connects to that model's public endpoint. A custom deployment also passes a websocket URL; the path in that URL doesn't select the model.

Slide text

Changed · RimeV1TTSService

Action required

RimeV1TTSService now needs an explicit model

1.13

RimeV1TTSService(
    api_key=os.environ["RIME_API_KEY"],
    settings=RimeV1TTSService.Settings(

        voice="astra",
    ),
)

1.14.0

RimeV1TTSService(
    api_key=os.environ["RIME_API_KEY"],
    settings=RimeV1TTSService.Settings(
        model="coda",  # or "mistv3"
        voice="astra",
    ),
)

Some defaults change under you. Google Vertex moves to Gemini 3.8 Flash, because Vertex retires 3.6 Flash on November 19, 2026. NVIDIA moves to Nemotron 3.5 Super, and Speechify to Simba 3.5. And strip_markdown now reduces a link to its label, so the URL isn't read aloud. The right-hand column keeps the old behavior.

Slide text

Changed · defaults

Three default models moved, and strip_markdown drops link URLs

Service	New default	To keep the old one, set
Google Vertex	gemini-3.8-flash	model="gemini-3.6-flash" retired by Vertex AI on 2026-11-19
NVIDIA	nemotron-3.5-super- vl-120b-a12b	model="nvidia/nemotron-3- super-120b-a12b"
Speechify HTTP	simba-3.5	model="simba-3.2"
strip_markdown	link → its label only	StripMarkdown(strip_urls=False)

Two deprecations can't wait. Perplexity has ended support for the Sonar API that PerplexityLLMService uses, so move to the Agent service. And workers on a shared bus now send tool schemas under a new module path, so upgrade them together. The rest keep working until 2.0.0.

Slide text

Deprecated

Do now

Move off PerplexityLLMService, and upgrade bus workers together

Perplexity has ended support for the Sonar API it uses. Workers on a shared bus send tool schemas under a new module path.

Still works until 2.0.0

text_filters → text_transforms

MarkdownTextFilter → strip_markdown

pipecat.adapters.schemas
→ pipecat.adapters.llm.schemas

RTVI text_type → output_type

redact_secrets, which ErrorFrame uses, left a credential unmasked when its pair followed another pair, like this API key after an error prefix. Now the prefix doesn't change what gets masked. And the minimum aiohttp is now 3.14.4, the first release with fixes for several of its security advisories.

Slide text

Security

redact_secrets no longer misses a credential after an error prefix

Left unmasked in 1.13, masked in 1.14.0

Unknown error occurred: api_key: abc123
ValueError: Authorization: Bearer abc123

pyproject.toml

"aiohttp>=3.14.0,<4",

"aiohttp>=3.14.4,<4",

One limit: audio that arrives while a speech-to-text connection is down still isn't transcribed. Before you upgrade, set a model on any Rime V1 service, move Perplexity to the Agent service, and upgrade workers that share a bus together. Then install 1.14.0, and a stuck connection stops freezing your bot.

Slide text

Upgrade · v1.14.0

One limit

Audio that arrives while a speech-to-text connection is down still isn't transcribed

Before you upgrade

Set model on every RimeV1TTSService

Move Perplexity to the Agent service

Upgrade bus workers together

$ uv add "pipecat-ai==1.14.0"