Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.getpatter.com/llms.txt

Use this file to discover all available pages before exploring further.

​
Inworld TTS

InworldTTS targets the Inworld TTS HTTP endpoint (POST https://api.inworld.ai/tts/v1/voice:stream). The response is NDJSON — one JSON object per line of the form {"result": {"audioContent": "<base64>", "timestampInfo": ...}} — and the provider yields the base64-decoded audio chunks as they arrive. The default model is inworld-tts-2 (sub-200 ms time-to-first-audio, 100+ languages with mid-utterance switching, natural-language voice steering). Pass model="inworld-tts-1.5-max" to fall back to the prior generation when you need temperature control. The default audio output is PCM_S16LE @ 16 kHz so chunks drop straight into the Patter pipeline without transcoding.

​
Install

pip install "getpatter[inworld]"
The getpatter[inworld] extra adds aiohttp>=3.10 for streaming the NDJSON body. (TypeScript uses native fetch and needs no extra dependency.)

​
Authentication

The Inworld dashboard issues a Base64 token that is already in the form expected by the Authorization: Basic <token> header — paste it into INWORLD_API_KEY as-is. Do not re-encode it.If you only have the raw API key string, base64-encode "<api_key>:" (note the trailing colon) yourself before passing it in.
export INWORLD_API_KEY="<base64-token-from-inworld-dashboard>"

​
Usage

# Namespaced import (pipeline mode)
from getpatter.tts import inworld

tts = inworld.TTS()                                       # reads INWORLD_API_KEY
tts = inworld.TTS(api_key="...", voice="Olivia", language="en")

# Flat alias (equivalent)
from getpatter import InworldTTS

tts = InworldTTS()
Plug it into an agent: 
import asyncio
from getpatter import Patter, Twilio, DeepgramSTT, InworldTTS

phone = Patter(carrier=Twilio(), phone_number="+15550001234")

agent = phone.agent(
    stt=DeepgramSTT(),                                    # DEEPGRAM_API_KEY from env
    tts=InworldTTS(voice="Ashley"),                       # INWORLD_API_KEY from env
    system_prompt="You are a helpful assistant.",
)

asyncio.run(phone.serve(agent))

​
Customising delivery mode (TTS-2)

deliveryMode controls how expressive the TTS-2 voice is. Use EXPRESSIVE for warm conversational agents, STABLE when you want consistent, predictable prosody (e.g. for IVR-style read-backs), and BALANCED for the middle ground. 
from getpatter import InworldTTS

tts = InworldTTS(
    voice="Ashley",
    delivery_mode="EXPRESSIVE",                           # EXPRESSIVE | BALANCED | STABLE
    speaking_rate=1.05,                                   # 0.5–1.5
    language="en",                                        # BCP-47
)
deliveryMode is TTS-2 only — it is silently ignored by the TTS-1.5 family. Conversely temperature is TTS-1.5 only and ignored by TTS-2.

​
Switching to TTS-1.5 for temperature control

When you need sampling-temperature control (e.g. for more variation across multi-turn conversations), drop down to inworld-tts-1.5-max: 
from getpatter import InworldTTS

tts = InworldTTS(
    model="inworld-tts-1.5-max",
    voice="Olivia",
    temperature=0.7,                                      # TTS-1.5 only
    language="it",
)

​
Models

Model idFamilyNotes
inworld-tts-2TTS-2 (default)Sub-200 ms TTFA, 100+ languages, natural-language voice steering, deliveryMode support.
inworld-tts-1.5-maxTTS-1.5Higher fidelity legacy model, temperature support.
inworld-tts-1.5-miniTTS-1.5Lower latency legacy model.
inworld-tts-1-maxTTS-1Original generation.
inworld-tts-1TTS-1Original generation.

​
Options

PythonTypeScriptDefaultNotes
api_keyapiKey—Reads INWORLD_API_KEY when omitted. Base64 token from the Inworld dashboard.
modelmodel"inworld-tts-2"One of the model ids above.
voicevoice"Ashley"Inworld voice name (e.g. "Ashley", "Olivia", "Craig", "Remy").
languagelanguage—BCP-47 tag ("en", "it", "es", …).
audio_encodingaudioEncoding"PCM"PCM / LINEAR16 / OGG_OPUS / MP3.
sample_ratesampleRate16000Hz. Pipeline default; carrier transcoding handles 8 kHz mulaw automatically.
bitratebitrate64000Used for OGG_OPUS / MP3 encodings.
temperaturetemperature—TTS-1.5 only. Sampling temperature.
speaking_ratespeakingRate1.0Multiplier in [0.5, 1.5].
delivery_modedeliveryMode—TTS-2 only. "EXPRESSIVE" / "BALANCED" / "STABLE".
base_urlbaseUrlInworld /tts/v1/voice:streamOverride for proxying or on-prem deployments.

​
Low-level usage

If you want the streaming generator without going through the pipeline-mode wrapper: 
from getpatter.providers.inworld_tts import InworldTTS as _LowLevelTTS

tts = _LowLevelTTS(
    auth_token="...",                                     # or INWORLD_API_KEY env var
    model="inworld-tts-2",
    voice="Ashley",
    sample_rate=16000,
)

async for pcm_chunk in tts.synthesize("Hello from the Patter pipeline."):
    ...                                                   # raw PCM_S16LE @ 16 kHz

await tts.close()

​
Pricing

The default rate in pricing.py is $0.020 / 1k characters for inworld-tts-2, with $0.025 / 1k for the TTS-1.5 family. These are placeholder defaults — verify against your current Inworld platform tier and override per-project via Patter(pricing={...}) if needed.