mosaic/stack
1
0
Fork 0
Code Issues 10 Pull Requests Actions Packages Projects Releases 2 Wiki Activity

Implement tiered TTS provider architecture #391

New Issue
Closed
opened 2026-02-15 07:33:32 +00:00 by jason.woltje · 1 comment
jason.woltje commented 2026-02-15 07:33:32 +00:00
Owner
Copy Link

Description

Implement the tiered TTS provider system with three backends, all using the OpenAI-compatible endpoint pattern.

Tiers

Default: Kokoro-FastAPI

  • URL:
  • Runs on CPU, always available
  • 54 voices, 8 languages
  • Apache 2.0 license

Premium: Chatterbox-TTS-Server

  • URL:
  • Requires GPU, optional deployment
  • Voice cloning from reference audio
  • Emotion control parameter
  • MIT license

Lightweight: Piper via OpenedAI Speech

  • URL:
  • Ultra-lightweight CPU fallback
  • 100+ voices, 40+ languages
  • GPL license

Provider Selection Logic

Environment Variables

Acceptance Criteria

  • KokoroTtsProvider implements ITTSProvider
  • ChatterboxTtsProvider implements ITTSProvider (voice cloning support)
  • PiperTtsProvider implements ITTSProvider
  • Fallback chain works (premium → default → lightweight)
  • Each provider configurable via environment variables
  • Unit tests for each provider + fallback logic
## Description Implement the tiered TTS provider system with three backends, all using the OpenAI-compatible endpoint pattern. ## Tiers ### Default: Kokoro-FastAPI - URL: - Runs on CPU, always available - 54 voices, 8 languages - Apache 2.0 license ### Premium: Chatterbox-TTS-Server - URL: - Requires GPU, optional deployment - Voice cloning from reference audio - Emotion control parameter - MIT license ### Lightweight: Piper via OpenedAI Speech - URL: - Ultra-lightweight CPU fallback - 100+ voices, 40+ languages - GPL license ## Provider Selection Logic ## Environment Variables ## Acceptance Criteria - [ ] KokoroTtsProvider implements ITTSProvider - [ ] ChatterboxTtsProvider implements ITTSProvider (voice cloning support) - [ ] PiperTtsProvider implements ITTSProvider - [ ] Fallback chain works (premium → default → lightweight) - [ ] Each provider configurable via environment variables - [ ] Unit tests for each provider + fallback logic
jason.woltje added this to the M13-SpeechServices (0.0.13) milestone 2026-02-15 07:33:32 +00:00
jason.woltje commented 2026-02-15 09:30:12 +00:00
Author
Owner
Copy Link

Completed as part of M13-SpeechServices milestone on branch feature/m13-speech-services. SP-TTS-001: Tiered TTS provider architecture (commit b5edb4f, 30 tests). All quality gates passed (lint, typecheck, tests, security).

Completed as part of M13-SpeechServices milestone on branch feature/m13-speech-services. SP-TTS-001: Tiered TTS provider architecture (commit b5edb4f, 30 tests). All quality gates passed (lint, typecheck, tests, security).
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
ai
AI/LLM integration
 api
Backend/API work
 api
auth
Authentication
 database
database
Database/schema work
 devops
Docker/deployment
 docs
Documentation
 frontend
graph
knowledge-module
migration
Data migration
 orchestrator
Orchestrator service (apps/orchestrator/)
 p0
Critical priority
 p1
High priority
 p2
Medium priority
 p3
Low priority
 performance
Performance work
 phase-1
phase-2
phase-3
phase-4
phase-5
plugin
MoltBot plugin work
 search
security
Security-related
 setup
Initial setup
 testing
Testing/QA
 web
Frontend work
No Label
Milestone
No items
No Milestone M13-SpeechServices (0.0.13)
Projects
Clear projects
No project
Assignees
Clear assignees
jason.woltje
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: mosaic/stack#391
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?