AssemblyAI STT

Universal Streaming speech-to-text via AssemblyAI’s v3 WebSocket API.

AssemblyAI STT

Streaming speech-to-text via AssemblyAI’s Universal Streaming v3 API. Pure-aiohttp transport, no vendor SDK required.

Install

pip install "getpatter[assemblyai]"

Usage

Use the public STT class either namespaced or flat — both read from ASSEMBLYAI_API_KEY when api_key= is omitted.

# Namespaced import
from getpatter.stt import assemblyai

stt = assemblyai.STT()                                    # reads ASSEMBLYAI_API_KEY
stt = assemblyai.STT(api_key="aa_...")

# Flat alias (equivalent)
from getpatter import AssemblyAISTT

stt = AssemblyAISTT()

Plug it into an agent:

import asyncio
from getpatter import Patter, Twilio, AssemblyAISTT, ElevenLabsTTS

phone = Patter(carrier=Twilio(), phone_number="[phone]")

agent = phone.agent(
    stt=AssemblyAISTT(),                                  # ASSEMBLYAI_API_KEY from env
    tts=ElevenLabsTTS(voice_id="rachel"),                 # ELEVENLABS_API_KEY from env
    system_prompt="You are a helpful assistant.",
)

asyncio.run(phone.serve(agent))

Low-level usage

If you are building a custom pipeline outside phone.agent(), the low-level adapter stays importable:

from getpatter.providers.assemblyai_stt import AssemblyAISTT

stt = AssemblyAISTT(api_key="aa_...", model="universal-streaming-english")
await stt.connect()
await stt.send_audio(pcm_chunk)  # 16 kHz PCM s16le
async for t in stt.receive_transcripts():
    print(t.text, t.is_final, t.confidence)
await stt.close()

For Twilio (mulaw 8 kHz) use AssemblyAISTT.for_twilio(api_key=...).