Skip to main content
Speech-to-Text (STT) converts spoken audio into text. In a custom voice pipeline, STT sits between the call and the LLM: user speaks → STT transcribes → turn signal → LLM → TTS. See Voice Agents for the full wiring guide.

​
Quick Start

uv add "vision-agents[deepgram,inworld,getstream]"
Add keys to your .env: 
STREAM_API_KEY=...
STREAM_API_SECRET=...
DEEPGRAM_API_KEY=...

from dotenv import load_dotenv

from vision_agents.core import Agent, User
from vision_agents.plugins import deepgram, gemini, getstream, inworld

load_dotenv()

agent = Agent(
    edge=getstream.Edge(),
    agent_user=User(name="Assistant", id="agent"),
    instructions="You are a helpful voice assistant.",
    llm=gemini.LLM(),
    stt=deepgram.STT(eager_turn_detection=True),
    tts=inworld.TTS(),
)
The SDK captures audio from your Stream call and feeds it to the STT provider in real time. As people speak, you receive live transcripts.

​
Providers

PluginTurn detectionLatency modelIntegration
DeepgramYes (eager optional)StreamingDeepgram
ElevenLabsYes (VAD commit)StreamingElevenLabs
CartesiaYes (eager default)StreamingCartesia
AssemblyAIYesStreamingAssemblyAI
SarvamYesStreamingSarvam
Fast-WhisperNoLocal batch (~2s buffer)Fast-Whisper
WizperNoCloud (Fal.ai)Wizper
FishNoBatchFish
MistralNoStreamingMistral
Fast-Whisper runs locally on your machine. Wizper uses Fal.ai cloud — it is not a local model.
STT plugins without built-in turn detection need an external turn detection plugin, or the agent falls back to using the final transcript as the end-of-turn signal.

​
Transcripts

STT providers emit partial, replacement, and final transcripts. Subscribe to agent events to handle them in your application: 
from vision_agents.core.agents.events import UserTranscriptEvent

@agent.events.subscribe
async def on_transcript(event: UserTranscriptEvent):
    print(event.text)

​
Next Steps

Voice Agents

Wire STT into a full voice pipeline

Turn Detection

When the agent starts and stops listening