feat: add NeuTTS optional skill + local TTS provider backend#1657
Merged
Conversation
Add NeuTTS optional skill with CLI scaffold, bootstrap helper, and sample voice profile. Also fixes skills_hub.py to handle binary assets (WAV files) during skill installation. Changes: - optional-skills/mlops/models/neutts/ — skill + CLI scaffold - tools/skills_hub.py — binary asset support (read_bytes, write_bytes) - tests/tools/test_skills_hub.py — regression tests for binary assets
Add NeuTTS as a fourth TTS provider option alongside Edge, ElevenLabs, and OpenAI. NeuTTS runs fully on-device via neutts_cli — no API key needed. Provider behavior: - Explicit: set tts.provider to 'neutts' in config.yaml - Fallback: when Edge TTS is unavailable and neutts_cli is installed, automatically falls back to NeuTTS instead of failing - check_tts_requirements() now includes NeuTTS in availability checks NeuTTS outputs WAV natively. For Telegram voice bubbles, ffmpeg converts to Opus (same pattern as Edge TTS). Changes: - tools/tts_tool.py — _generate_neutts(), _check_neutts_available(), provider dispatch, fallback logic, Opus conversion - hermes_cli/config.py — tts.neutts config defaults
This was referenced Mar 17, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Salvaged from PR #1134 by @unmodeled-tyler, with TTS provider integration added per Teknium's direction.
Part 1: Optional skill (from PR #1134)
optional-skills/mlops/models/neutts/— full NeuTTS skill with CLI scaffold, bootstrap helper, sample voice profile, and collaborative voice design workflowtools/skills_hub.py— binary asset support so .wav files survive skill installationtests/tools/test_skills_hub.py— regression tests for binary asset handlingPart 2: TTS provider backend (new)
NeuTTS is now a first-class TTS provider alongside Edge, ElevenLabs, and OpenAI:
tts.provider: "neutts"in config.yamlneutts_cliis present, NeuTTS kicks in automatically instead of failingcheck_tts_requirements()includes NeuTTS in availability checks, so the TTS tool registers as available when neutts_cli is installed even if edge-tts isn'tConfig:
NeuTTS outputs WAV; ffmpeg converts to Opus for Telegram voice bubbles (same pattern as Edge TTS).
Files changed
tools/tts_tool.py—_generate_neutts(),_check_neutts_available(), provider dispatch, fallback logichermes_cli/config.py—tts.neuttsconfig defaultstools/skills_hub.py— binary file support (read_bytes/write_bytes)tests/tools/test_skills_hub.py— binary asset testsoptional-skills/mlops/models/neutts/— full skill + CLI scaffold