Skip to content

docs(inworld): default to inworld-tts-2; introduce Realtime TTS naming#795

Open
cshape wants to merge 1 commit intopipecat-ai:mainfrom
cshape:tts-2
Open

docs(inworld): default to inworld-tts-2; introduce Realtime TTS naming#795
cshape wants to merge 1 commit intopipecat-ai:mainfrom
cshape:tts-2

Conversation

@cshape
Copy link
Copy Markdown
Contributor

@cshape cshape commented May 5, 2026

Inworld TTS-2 default + Realtime TTS naming

Documents inworld-tts-2 as the new default for Pipecat's Inworld TTS and Realtime services. Keeps inworld-tts-1.5-max and inworld-tts-1.5-mini as documented options. Updates display naming to Realtime TTS-2 / Realtime TTS-1.5-Max / Realtime TTS-1.5-Mini per partner request.

Changes

  • api-reference/server/services/tts/inworld.mdx
    • Frontmatter description mentions Realtime TTS-2.
    • New Models section with display name → model ID table.
    • Flipped model defaults on InworldTTSService and InworldHttpTTSService from inworld-tts-1.5-max to inworld-tts-2 (param remains deprecated; Settings.model is preferred).
    • Updated usage example to use model="inworld-tts-2".
  • api-reference/server/services/s2s/inworld.mdx
    • Frontmatter description mentions Realtime TTS-2.
    • Overview now states the TTS default and lists the available Realtime TTS models.
    • tts_model default flipped from inworld-tts-1.5-max to inworld-tts-2; param description lists all three options with display names.
    • AudioOutput.model example, "With Model and Voice Configuration" example, and "With Full Session Configuration" example all updated to inworld-tts-2.

Test plan

  • Visual diff of both inworld.mdx files
  • grep -rn "inworld-tts-1.5-max" . — only option-listing mentions remain (no defaults / examples)
  • grep -rn "inworld-tts-2" . — appears as the default in all relevant defaults and examples

Flip the documented default for both InworldTTSService /
InworldHttpTTSService and InworldRealtimeLLMService.tts_model from
inworld-tts-1.5-max to inworld-tts-2. Keep inworld-tts-1.5-max and
inworld-tts-1.5-mini as documented options.

Add display-naming guidance per partner request: Realtime TTS-2,
Realtime TTS-1.5-Max, Realtime TTS-1.5-Mini.
Copy link
Copy Markdown
Contributor

@markbackman markbackman left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants