Inworld Streaming TTS Provider

Inworld functions as a streaming text-to-speech (TTS) provider. Within OpenClaw, it generates outbound reply audio, producing MP3 by default, OGG_OPUS for voice notes, and raw PCM audio for telephony channels like Voice Call.

OpenClaw sends requests to Inworld's streaming TTS endpoint, merges the returned base64 audio chunks into one buffer, then passes the result into the standard reply audio pipeline.

Property	Value
Provider id	`inworld`
Plugin	official external package (`@openclaw/inworld-speech`)
Contract	`speechProviders` (TTS only)
Auth env var	`INWORLD_API_KEY` (HTTP Basic, Base64 dashboard credential)
Base URL	`https://api.inworld.ai`
Default voice	`Sarah`
Default model	`inworld-tts-1.5-max`
Output	MP3 (default), OGG_OPUS (voice notes), PCM 22050 Hz (telephony)
Website	inworld.ai
Docs	docs.inworld.ai/tts/tts

Install plugin

openclaw plugins install @openclaw/inworld-speech
openclaw gateway restart

Getting started

Set your API key

Retrieve the credential from your Inworld dashboard under Workspace > API Keys and assign it as an environment variable. The value is transmitted exactly as the HTTP Basic credential, so avoid Base64 re-encoding or converting it into a bearer token.

INWORLD_API_KEY=<base64-credential-from-dashboard>

Select Inworld in tts

{
  tts: {
    auto: "always",
    provider: "inworld",
    providers: {
      inworld: {
        voiceId: "Sarah",
        modelId: "inworld-tts-1.5-max",
      },
    },
  },
}

Send a message

Send a reply through any connected channel. OpenClaw generates the audio using Inworld and delivers it as MP3, or OGG_OPUS when the channel expects a voice note.

Configuration options

Option	Path	Description
`apiKey`	`tts.providers.inworld.apiKey`	Base64 dashboard credential. Falls back to `INWORLD_API_KEY`.
`baseUrl`	`tts.providers.inworld.baseUrl`	Override Inworld API base URL (default `https://api.inworld.ai`).
`voiceId`	`tts.providers.inworld.voiceId`	Voice identifier (default `Sarah`). Legacy alias: `speakerVoiceId`.
`modelId`	`tts.providers.inworld.modelId`	TTS model id (default `inworld-tts-1.5-max`).
`temperature`	`tts.providers.inworld.temperature`	Sampling temperature, `0` (exclusive) to `2` (optional).

Notes

Authentication

Inworld relies on HTTP Basic authentication using a single Base64-encoded credential string. Copy it directly from the Inworld dashboard. The provider sends it as Authorization: Basic <apiKey> without additional encoding, so do not Base64-encode it yourself and avoid passing a bearer-style token. The same reminder appears in the TTS auth notes.

Models

Supported model identifiers: inworld-tts-1.5-max (default), inworld-tts-1.5-mini, inworld-tts-1-max, inworld-tts-1.

Audio outputs

Replies default to MP3. When the channel target is voice-note, OpenClaw requests OGG_OPUS from Inworld so the audio plays as a native voice bubble. Telephony synthesis uses raw PCM at 22050 Hz to supply the telephony bridge.

Custom endpoints

Override the API host using tts.providers.inworld.baseUrl. Trailing slashes are removed before requests are dispatched.

Text-to-speech, Overview of TTS, providers, and tts configuration.
Configuration, Full configuration reference including tts settings.
Providers, All supported OpenClaw providers.
Troubleshooting, Common problems and debugging steps.