feat(tts): add Piper as a native local TTS provider (closes #8508)#17885
Merged
Conversation
Piper (OHF-Voice/piper1-gpl) is a fast, local neural TTS engine from the
Home Assistant project that supports 44 languages with zero API keys.
Adds it as a native built-in provider alongside edge/neutts/kittentts,
installable via 'hermes tools' with one keystroke.
What ships:
- New 'piper' built-in provider in tools/tts_tool.py
- Lazy import via _import_piper()
- Module-level voice cache keyed on (model_path, use_cuda) so switching
voices doesn't invalidate older cached voices
- _resolve_piper_voice_path() accepts either an absolute .onnx path or a
voice name (auto-downloaded on first use via 'python -m
piper.download_voices --download-dir <cache>')
- Voice cache at ~/.hermes/cache/piper-voices/ (profile-aware via
get_hermes_dir)
- Optional SynthesisConfig knobs: length_scale, noise_scale,
noise_w_scale, volume, normalize_audio, use_cuda — passed through
only when configured, so older piper-tts versions aren't broken
- WAV output then ffmpeg conversion path (same as neutts/kittentts) so
Telegram voice bubbles work when ffmpeg is present
- Piper added to BUILTIN_TTS_PROVIDERS so a user's
tts.providers.piper.command cannot shadow the native provider
(regression test included)
- 'hermes tools' wizard entry
- Piper appears under Voice and TTS as local free, with
'pip install piper-tts' auto-install via post_setup handler
- Prints voice-catalog URL and default-voice info after install
- config.yaml defaults
- tts.piper.voice defaults to en_US-lessac-medium
- Commented advanced knobs for discoverability
- Docs
- New 'Piper (local, 44 languages)' section in features/tts.md
explaining install path, voice switching, pre-downloaded voices,
and advanced knobs
- Piper listed in the ten-provider table and ffmpeg table
- Custom-command-providers section updated to drop the Piper example
(now native) and add a piper-custom example for users with their own
trained .onnx models
- overview.md bumps provider count to ten
- Tests (tests/tools/test_tts_piper.py, 16 tests)
- Registration (BUILTIN_TTS_PROVIDERS, PROVIDER_MAX_TEXT_LENGTH)
- _resolve_piper_voice_path across every branch: direct .onnx path,
cached voice name, fresh download with correct CLI args, download
failure, successful-exit-but-missing-files, empty voice to default
- _generate_piper_tts: loads voice once, reuses cache, voice-name
download wiring, advanced knobs flow through SynthesisConfig
- text_to_speech_tool end-to-end dispatch and missing-package error
- check_tts_requirements: piper availability toggles the return value
- Regression guard: piper cannot be shadowed by a command provider
with the same name
- Pre-existing test_tts_mistral test broadened to mock the new
piper/kittentts/command-provider checks (otherwise it false-passes
when piper is installed in the test venv)
E2E verification (live):
Actual pip install piper-tts, config piper + en_US-lessac-low,
text_to_speech_tool call, voice auto-downloaded from HuggingFace,
WAV synthesized, ffmpeg-converted to Ogg/Opus. Second call hits the
cache (~60ms). Cache dir populated with .onnx and .onnx.json.
This caught a real bug during development: the first pass used '-d' as
the download-dir flag; the actual piper.download_voices CLI wants
'--download-dir'. Fixed before PR opened.
This was referenced Apr 30, 2026
19 tasks
cluricaun28
referenced
this pull request
in cluricaun28/Logos
Apr 30, 2026
…17885)
Piper (OHF-Voice/piper1-gpl) is a fast, local neural TTS engine from the
Home Assistant project that supports 44 languages with zero API keys.
Adds it as a native built-in provider alongside edge/neutts/kittentts,
installable via 'hermes tools' with one keystroke.
What ships:
- New 'piper' built-in provider in tools/tts_tool.py
- Lazy import via _import_piper()
- Module-level voice cache keyed on (model_path, use_cuda) so switching
voices doesn't invalidate older cached voices
- _resolve_piper_voice_path() accepts either an absolute .onnx path or a
voice name (auto-downloaded on first use via 'python -m
piper.download_voices --download-dir <cache>')
- Voice cache at ~/.hermes/cache/piper-voices/ (profile-aware via
get_hermes_dir)
- Optional SynthesisConfig knobs: length_scale, noise_scale,
noise_w_scale, volume, normalize_audio, use_cuda — passed through
only when configured, so older piper-tts versions aren't broken
- WAV output then ffmpeg conversion path (same as neutts/kittentts) so
Telegram voice bubbles work when ffmpeg is present
- Piper added to BUILTIN_TTS_PROVIDERS so a user's
tts.providers.piper.command cannot shadow the native provider
(regression test included)
- 'hermes tools' wizard entry
- Piper appears under Voice and TTS as local free, with
'pip install piper-tts' auto-install via post_setup handler
- Prints voice-catalog URL and default-voice info after install
- config.yaml defaults
- tts.piper.voice defaults to en_US-lessac-medium
- Commented advanced knobs for discoverability
- Docs
- New 'Piper (local, 44 languages)' section in features/tts.md
explaining install path, voice switching, pre-downloaded voices,
and advanced knobs
- Piper listed in the ten-provider table and ffmpeg table
- Custom-command-providers section updated to drop the Piper example
(now native) and add a piper-custom example for users with their own
trained .onnx models
- overview.md bumps provider count to ten
- Tests (tests/tools/test_tts_piper.py, 16 tests)
- Registration (BUILTIN_TTS_PROVIDERS, PROVIDER_MAX_TEXT_LENGTH)
- _resolve_piper_voice_path across every branch: direct .onnx path,
cached voice name, fresh download with correct CLI args, download
failure, successful-exit-but-missing-files, empty voice to default
- _generate_piper_tts: loads voice once, reuses cache, voice-name
download wiring, advanced knobs flow through SynthesisConfig
- text_to_speech_tool end-to-end dispatch and missing-package error
- check_tts_requirements: piper availability toggles the return value
- Regression guard: piper cannot be shadowed by a command provider
with the same name
- Pre-existing test_tts_mistral test broadened to mock the new
piper/kittentts/command-provider checks (otherwise it false-passes
when piper is installed in the test venv)
E2E verification (live):
Actual pip install piper-tts, config piper + en_US-lessac-low,
text_to_speech_tool call, voice auto-downloaded from HuggingFace,
WAV synthesized, ffmpeg-converted to Ogg/Opus. Second call hits the
cache (~60ms). Cache dir populated with .onnx and .onnx.json.
This caught a real bug during development: the first pass used '-d' as
the download-dir flag; the actual piper.download_voices CLI wants
'--download-dir'. Fixed before PR opened.
nickdlkk
pushed a commit
to nickdlkk/hermes-agent
that referenced
this pull request
May 11, 2026
…rch#8508) (NousResearch#17885) Piper (OHF-Voice/piper1-gpl) is a fast, local neural TTS engine from the Home Assistant project that supports 44 languages with zero API keys. Adds it as a native built-in provider alongside edge/neutts/kittentts, installable via 'hermes tools' with one keystroke. What ships: - New 'piper' built-in provider in tools/tts_tool.py - Lazy import via _import_piper() - Module-level voice cache keyed on (model_path, use_cuda) so switching voices doesn't invalidate older cached voices - _resolve_piper_voice_path() accepts either an absolute .onnx path or a voice name (auto-downloaded on first use via 'python -m piper.download_voices --download-dir <cache>') - Voice cache at ~/.hermes/cache/piper-voices/ (profile-aware via get_hermes_dir) - Optional SynthesisConfig knobs: length_scale, noise_scale, noise_w_scale, volume, normalize_audio, use_cuda — passed through only when configured, so older piper-tts versions aren't broken - WAV output then ffmpeg conversion path (same as neutts/kittentts) so Telegram voice bubbles work when ffmpeg is present - Piper added to BUILTIN_TTS_PROVIDERS so a user's tts.providers.piper.command cannot shadow the native provider (regression test included) - 'hermes tools' wizard entry - Piper appears under Voice and TTS as local free, with 'pip install piper-tts' auto-install via post_setup handler - Prints voice-catalog URL and default-voice info after install - config.yaml defaults - tts.piper.voice defaults to en_US-lessac-medium - Commented advanced knobs for discoverability - Docs - New 'Piper (local, 44 languages)' section in features/tts.md explaining install path, voice switching, pre-downloaded voices, and advanced knobs - Piper listed in the ten-provider table and ffmpeg table - Custom-command-providers section updated to drop the Piper example (now native) and add a piper-custom example for users with their own trained .onnx models - overview.md bumps provider count to ten - Tests (tests/tools/test_tts_piper.py, 16 tests) - Registration (BUILTIN_TTS_PROVIDERS, PROVIDER_MAX_TEXT_LENGTH) - _resolve_piper_voice_path across every branch: direct .onnx path, cached voice name, fresh download with correct CLI args, download failure, successful-exit-but-missing-files, empty voice to default - _generate_piper_tts: loads voice once, reuses cache, voice-name download wiring, advanced knobs flow through SynthesisConfig - text_to_speech_tool end-to-end dispatch and missing-package error - check_tts_requirements: piper availability toggles the return value - Regression guard: piper cannot be shadowed by a command provider with the same name - Pre-existing test_tts_mistral test broadened to mock the new piper/kittentts/command-provider checks (otherwise it false-passes when piper is installed in the test venv) E2E verification (live): Actual pip install piper-tts, config piper + en_US-lessac-low, text_to_speech_tool call, voice auto-downloaded from HuggingFace, WAV synthesized, ffmpeg-converted to Ogg/Opus. Second call hits the cache (~60ms). Cache dir populated with .onnx and .onnx.json. This caught a real bug during development: the first pass used '-d' as the download-dir flag; the actual piper.download_voices CLI wants '--download-dir'. Fixed before PR opened.
Closed
4 tasks
02356abc
pushed a commit
to 02356abc/hermes-agent
that referenced
this pull request
May 14, 2026
…rch#8508) (NousResearch#17885) Piper (OHF-Voice/piper1-gpl) is a fast, local neural TTS engine from the Home Assistant project that supports 44 languages with zero API keys. Adds it as a native built-in provider alongside edge/neutts/kittentts, installable via 'hermes tools' with one keystroke. What ships: - New 'piper' built-in provider in tools/tts_tool.py - Lazy import via _import_piper() - Module-level voice cache keyed on (model_path, use_cuda) so switching voices doesn't invalidate older cached voices - _resolve_piper_voice_path() accepts either an absolute .onnx path or a voice name (auto-downloaded on first use via 'python -m piper.download_voices --download-dir <cache>') - Voice cache at ~/.hermes/cache/piper-voices/ (profile-aware via get_hermes_dir) - Optional SynthesisConfig knobs: length_scale, noise_scale, noise_w_scale, volume, normalize_audio, use_cuda — passed through only when configured, so older piper-tts versions aren't broken - WAV output then ffmpeg conversion path (same as neutts/kittentts) so Telegram voice bubbles work when ffmpeg is present - Piper added to BUILTIN_TTS_PROVIDERS so a user's tts.providers.piper.command cannot shadow the native provider (regression test included) - 'hermes tools' wizard entry - Piper appears under Voice and TTS as local free, with 'pip install piper-tts' auto-install via post_setup handler - Prints voice-catalog URL and default-voice info after install - config.yaml defaults - tts.piper.voice defaults to en_US-lessac-medium - Commented advanced knobs for discoverability - Docs - New 'Piper (local, 44 languages)' section in features/tts.md explaining install path, voice switching, pre-downloaded voices, and advanced knobs - Piper listed in the ten-provider table and ffmpeg table - Custom-command-providers section updated to drop the Piper example (now native) and add a piper-custom example for users with their own trained .onnx models - overview.md bumps provider count to ten - Tests (tests/tools/test_tts_piper.py, 16 tests) - Registration (BUILTIN_TTS_PROVIDERS, PROVIDER_MAX_TEXT_LENGTH) - _resolve_piper_voice_path across every branch: direct .onnx path, cached voice name, fresh download with correct CLI args, download failure, successful-exit-but-missing-files, empty voice to default - _generate_piper_tts: loads voice once, reuses cache, voice-name download wiring, advanced knobs flow through SynthesisConfig - text_to_speech_tool end-to-end dispatch and missing-package error - check_tts_requirements: piper availability toggles the return value - Regression guard: piper cannot be shadowed by a command provider with the same name - Pre-existing test_tts_mistral test broadened to mock the new piper/kittentts/command-provider checks (otherwise it false-passes when piper is installed in the test venv) E2E verification (live): Actual pip install piper-tts, config piper + en_US-lessac-low, text_to_speech_tool call, voice auto-downloaded from HuggingFace, WAV synthesized, ffmpeg-converted to Ogg/Opus. Second call hits the cache (~60ms). Cache dir populated with .onnx and .onnx.json. This caught a real bug during development: the first pass used '-d' as the download-dir flag; the actual piper.download_voices CLI wants '--download-dir'. Fixed before PR opened.
jsboige
pushed a commit
to jsboige/hermes-agent
that referenced
this pull request
May 14, 2026
…rch#8508) (NousResearch#17885) Piper (OHF-Voice/piper1-gpl) is a fast, local neural TTS engine from the Home Assistant project that supports 44 languages with zero API keys. Adds it as a native built-in provider alongside edge/neutts/kittentts, installable via 'hermes tools' with one keystroke. What ships: - New 'piper' built-in provider in tools/tts_tool.py - Lazy import via _import_piper() - Module-level voice cache keyed on (model_path, use_cuda) so switching voices doesn't invalidate older cached voices - _resolve_piper_voice_path() accepts either an absolute .onnx path or a voice name (auto-downloaded on first use via 'python -m piper.download_voices --download-dir <cache>') - Voice cache at ~/.hermes/cache/piper-voices/ (profile-aware via get_hermes_dir) - Optional SynthesisConfig knobs: length_scale, noise_scale, noise_w_scale, volume, normalize_audio, use_cuda — passed through only when configured, so older piper-tts versions aren't broken - WAV output then ffmpeg conversion path (same as neutts/kittentts) so Telegram voice bubbles work when ffmpeg is present - Piper added to BUILTIN_TTS_PROVIDERS so a user's tts.providers.piper.command cannot shadow the native provider (regression test included) - 'hermes tools' wizard entry - Piper appears under Voice and TTS as local free, with 'pip install piper-tts' auto-install via post_setup handler - Prints voice-catalog URL and default-voice info after install - config.yaml defaults - tts.piper.voice defaults to en_US-lessac-medium - Commented advanced knobs for discoverability - Docs - New 'Piper (local, 44 languages)' section in features/tts.md explaining install path, voice switching, pre-downloaded voices, and advanced knobs - Piper listed in the ten-provider table and ffmpeg table - Custom-command-providers section updated to drop the Piper example (now native) and add a piper-custom example for users with their own trained .onnx models - overview.md bumps provider count to ten - Tests (tests/tools/test_tts_piper.py, 16 tests) - Registration (BUILTIN_TTS_PROVIDERS, PROVIDER_MAX_TEXT_LENGTH) - _resolve_piper_voice_path across every branch: direct .onnx path, cached voice name, fresh download with correct CLI args, download failure, successful-exit-but-missing-files, empty voice to default - _generate_piper_tts: loads voice once, reuses cache, voice-name download wiring, advanced knobs flow through SynthesisConfig - text_to_speech_tool end-to-end dispatch and missing-package error - check_tts_requirements: piper availability toggles the return value - Regression guard: piper cannot be shadowed by a command provider with the same name - Pre-existing test_tts_mistral test broadened to mock the new piper/kittentts/command-provider checks (otherwise it false-passes when piper is installed in the test venv) E2E verification (live): Actual pip install piper-tts, config piper + en_US-lessac-low, text_to_speech_tool call, voice auto-downloaded from HuggingFace, WAV synthesized, ffmpeg-converted to Ogg/Opus. Second call hits the cache (~60ms). Cache dir populated with .onnx and .onnx.json. This caught a real bug during development: the first pass used '-d' as the download-dir flag; the actual piper.download_voices CLI wants '--download-dir'. Fixed before PR opened.
dannyJ848
pushed a commit
to dannyJ848/hermes-agent
that referenced
this pull request
May 17, 2026
…rch#8508) (NousResearch#17885) Piper (OHF-Voice/piper1-gpl) is a fast, local neural TTS engine from the Home Assistant project that supports 44 languages with zero API keys. Adds it as a native built-in provider alongside edge/neutts/kittentts, installable via 'hermes tools' with one keystroke. What ships: - New 'piper' built-in provider in tools/tts_tool.py - Lazy import via _import_piper() - Module-level voice cache keyed on (model_path, use_cuda) so switching voices doesn't invalidate older cached voices - _resolve_piper_voice_path() accepts either an absolute .onnx path or a voice name (auto-downloaded on first use via 'python -m piper.download_voices --download-dir <cache>') - Voice cache at ~/.hermes/cache/piper-voices/ (profile-aware via get_hermes_dir) - Optional SynthesisConfig knobs: length_scale, noise_scale, noise_w_scale, volume, normalize_audio, use_cuda — passed through only when configured, so older piper-tts versions aren't broken - WAV output then ffmpeg conversion path (same as neutts/kittentts) so Telegram voice bubbles work when ffmpeg is present - Piper added to BUILTIN_TTS_PROVIDERS so a user's tts.providers.piper.command cannot shadow the native provider (regression test included) - 'hermes tools' wizard entry - Piper appears under Voice and TTS as local free, with 'pip install piper-tts' auto-install via post_setup handler - Prints voice-catalog URL and default-voice info after install - config.yaml defaults - tts.piper.voice defaults to en_US-lessac-medium - Commented advanced knobs for discoverability - Docs - New 'Piper (local, 44 languages)' section in features/tts.md explaining install path, voice switching, pre-downloaded voices, and advanced knobs - Piper listed in the ten-provider table and ffmpeg table - Custom-command-providers section updated to drop the Piper example (now native) and add a piper-custom example for users with their own trained .onnx models - overview.md bumps provider count to ten - Tests (tests/tools/test_tts_piper.py, 16 tests) - Registration (BUILTIN_TTS_PROVIDERS, PROVIDER_MAX_TEXT_LENGTH) - _resolve_piper_voice_path across every branch: direct .onnx path, cached voice name, fresh download with correct CLI args, download failure, successful-exit-but-missing-files, empty voice to default - _generate_piper_tts: loads voice once, reuses cache, voice-name download wiring, advanced knobs flow through SynthesisConfig - text_to_speech_tool end-to-end dispatch and missing-package error - check_tts_requirements: piper availability toggles the return value - Regression guard: piper cannot be shadowed by a command provider with the same name - Pre-existing test_tts_mistral test broadened to mock the new piper/kittentts/command-provider checks (otherwise it false-passes when piper is installed in the test venv) E2E verification (live): Actual pip install piper-tts, config piper + en_US-lessac-low, text_to_speech_tool call, voice auto-downloaded from HuggingFace, WAV synthesized, ffmpeg-converted to Ogg/Opus. Second call hits the cache (~60ms). Cache dir populated with .onnx and .onnx.json. This caught a real bug during development: the first pass used '-d' as the download-dir flag; the actual piper.download_voices CLI wants '--download-dir'. Fixed before PR opened.
gweeteve
pushed a commit
to gweeteve/hermes-agent
that referenced
this pull request
Jun 2, 2026
…rch#8508) (NousResearch#17885) Piper (OHF-Voice/piper1-gpl) is a fast, local neural TTS engine from the Home Assistant project that supports 44 languages with zero API keys. Adds it as a native built-in provider alongside edge/neutts/kittentts, installable via 'hermes tools' with one keystroke. What ships: - New 'piper' built-in provider in tools/tts_tool.py - Lazy import via _import_piper() - Module-level voice cache keyed on (model_path, use_cuda) so switching voices doesn't invalidate older cached voices - _resolve_piper_voice_path() accepts either an absolute .onnx path or a voice name (auto-downloaded on first use via 'python -m piper.download_voices --download-dir <cache>') - Voice cache at ~/.hermes/cache/piper-voices/ (profile-aware via get_hermes_dir) - Optional SynthesisConfig knobs: length_scale, noise_scale, noise_w_scale, volume, normalize_audio, use_cuda — passed through only when configured, so older piper-tts versions aren't broken - WAV output then ffmpeg conversion path (same as neutts/kittentts) so Telegram voice bubbles work when ffmpeg is present - Piper added to BUILTIN_TTS_PROVIDERS so a user's tts.providers.piper.command cannot shadow the native provider (regression test included) - 'hermes tools' wizard entry - Piper appears under Voice and TTS as local free, with 'pip install piper-tts' auto-install via post_setup handler - Prints voice-catalog URL and default-voice info after install - config.yaml defaults - tts.piper.voice defaults to en_US-lessac-medium - Commented advanced knobs for discoverability - Docs - New 'Piper (local, 44 languages)' section in features/tts.md explaining install path, voice switching, pre-downloaded voices, and advanced knobs - Piper listed in the ten-provider table and ffmpeg table - Custom-command-providers section updated to drop the Piper example (now native) and add a piper-custom example for users with their own trained .onnx models - overview.md bumps provider count to ten - Tests (tests/tools/test_tts_piper.py, 16 tests) - Registration (BUILTIN_TTS_PROVIDERS, PROVIDER_MAX_TEXT_LENGTH) - _resolve_piper_voice_path across every branch: direct .onnx path, cached voice name, fresh download with correct CLI args, download failure, successful-exit-but-missing-files, empty voice to default - _generate_piper_tts: loads voice once, reuses cache, voice-name download wiring, advanced knobs flow through SynthesisConfig - text_to_speech_tool end-to-end dispatch and missing-package error - check_tts_requirements: piper availability toggles the return value - Regression guard: piper cannot be shadowed by a command provider with the same name - Pre-existing test_tts_mistral test broadened to mock the new piper/kittentts/command-provider checks (otherwise it false-passes when piper is installed in the test venv) E2E verification (live): Actual pip install piper-tts, config piper + en_US-lessac-low, text_to_speech_tool call, voice auto-downloaded from HuggingFace, WAV synthesized, ffmpeg-converted to Ogg/Opus. Second call hits the cache (~60ms). Cache dir populated with .onnx and .onnx.json. This caught a real bug during development: the first pass used '-d' as the download-dir flag; the actual piper.download_voices CLI wants '--download-dir'. Fixed before PR opened.
Egavasyug
pushed a commit
to Egavasyug/hermes-agent
that referenced
this pull request
Jun 10, 2026
…rch#8508) (NousResearch#17885) Piper (OHF-Voice/piper1-gpl) is a fast, local neural TTS engine from the Home Assistant project that supports 44 languages with zero API keys. Adds it as a native built-in provider alongside edge/neutts/kittentts, installable via 'hermes tools' with one keystroke. What ships: - New 'piper' built-in provider in tools/tts_tool.py - Lazy import via _import_piper() - Module-level voice cache keyed on (model_path, use_cuda) so switching voices doesn't invalidate older cached voices - _resolve_piper_voice_path() accepts either an absolute .onnx path or a voice name (auto-downloaded on first use via 'python -m piper.download_voices --download-dir <cache>') - Voice cache at ~/.hermes/cache/piper-voices/ (profile-aware via get_hermes_dir) - Optional SynthesisConfig knobs: length_scale, noise_scale, noise_w_scale, volume, normalize_audio, use_cuda — passed through only when configured, so older piper-tts versions aren't broken - WAV output then ffmpeg conversion path (same as neutts/kittentts) so Telegram voice bubbles work when ffmpeg is present - Piper added to BUILTIN_TTS_PROVIDERS so a user's tts.providers.piper.command cannot shadow the native provider (regression test included) - 'hermes tools' wizard entry - Piper appears under Voice and TTS as local free, with 'pip install piper-tts' auto-install via post_setup handler - Prints voice-catalog URL and default-voice info after install - config.yaml defaults - tts.piper.voice defaults to en_US-lessac-medium - Commented advanced knobs for discoverability - Docs - New 'Piper (local, 44 languages)' section in features/tts.md explaining install path, voice switching, pre-downloaded voices, and advanced knobs - Piper listed in the ten-provider table and ffmpeg table - Custom-command-providers section updated to drop the Piper example (now native) and add a piper-custom example for users with their own trained .onnx models - overview.md bumps provider count to ten - Tests (tests/tools/test_tts_piper.py, 16 tests) - Registration (BUILTIN_TTS_PROVIDERS, PROVIDER_MAX_TEXT_LENGTH) - _resolve_piper_voice_path across every branch: direct .onnx path, cached voice name, fresh download with correct CLI args, download failure, successful-exit-but-missing-files, empty voice to default - _generate_piper_tts: loads voice once, reuses cache, voice-name download wiring, advanced knobs flow through SynthesisConfig - text_to_speech_tool end-to-end dispatch and missing-package error - check_tts_requirements: piper availability toggles the return value - Regression guard: piper cannot be shadowed by a command provider with the same name - Pre-existing test_tts_mistral test broadened to mock the new piper/kittentts/command-provider checks (otherwise it false-passes when piper is installed in the test venv) E2E verification (live): Actual pip install piper-tts, config piper + en_US-lessac-low, text_to_speech_tool call, voice auto-downloaded from HuggingFace, WAV synthesized, ffmpeg-converted to Ogg/Opus. Second call hits the cache (~60ms). Cache dir populated with .onnx and .onnx.json. This caught a real bug during development: the first pass used '-d' as the download-dir flag; the actual piper.download_voices CLI wants '--download-dir'. Fixed before PR opened.
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
Closes #8508. Adds Piper (OHF-Voice/piper1-gpl) as a native local TTS provider — fast neural TTS with 44 languages, zero API keys. One-keystroke install via
hermes tools.What a user does
Hermes runs
pip install piper-tts. Then:On the first TTS call, Hermes downloads the voice (~20-90MB depending on quality tier) into
~/.hermes/cache/piper-voices/and reuses it forever after. Voice catalog: 44 languages at OHF-Voice/piper1-gpl VOICES.md.Changes
tools/tts_tool.py_import_piper,_check_piper_available,_resolve_piper_voice_path(path OR voice name with auto-download),_generate_piper_tts(module-cached voice, optionalSynthesisConfigknobs). Wired intotext_to_speech_tool,check_tts_requirements, and the ffmpeg-opus conversion branch.piperadded toBUILTIN_TTS_PROVIDERSandPROVIDER_MAX_TEXT_LENGTH.hermes_cli/tools_config.pypost_setuphandler that runspip install piper-ttsand prints voice-catalog URL.hermes_cli/config.pytts.piper.voice = en_US-lessac-mediumdefault + commented advanced knobs.website/docs/user-guide/features/tts.mdwebsite/docs/user-guide/features/overview.mdtests/tools/test_tts_piper.pycheck_tts_requirementstoggle, shadow-protection regression guard.E2E verification (live, on-machine)
pip install piper-tts(inside repo venv)tts.provider: piper,tts.piper.voice: en_US-lessac-low(~14MB tier)text_to_speech_tool(text="Hello from Piper in Hermes Agent!")→ voice auto-downloaded from HuggingFace, WAV synthesized, ffmpeg-converted to Ogg/Opus (validOggSheader).en_US-lessac-low.onnx+en_US-lessac-low.onnx.json.E2E caught a real bug: the first pass used
-das the download-dir flag, butpython -m piper.download_voicesactually wants--download-dir. Fixed before opening this PR. Unit tests alone would not have caught it.Why native instead of command provider
Native Piper addresses what #8508 actually asked for: broader local-language coverage that just works from
hermes setup. The shell command-provider path (landed in #17843) still exists for custom workflows — users with their own trained.onnxmodels can settts.piper.voiceto an absolute path, or go full command-provider for non-standard wrappers. Both paths documented.Validation
tests/tools/test_tts_piper.py— 16 passedRelation to #17211 / #17843
This is PR 3 in the three-part redesign:
Together these make Hermes first-class for both casual users ("I want Piper working") and power users ("I want to wire in my custom CLI").