voice-for-agent
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
voice-for-agent
Output-only text-to-speech for AI agents. The agent writes text; this tool cleans it, speaks it, and gets out of the way. There is no microphone, no speech-to-text, and no realtime duplex chat.
Primary engine:
edge-tts(online, natural neural voices).Offline fallback:
piperwith a local voice model.Playback:
mpv, thenffplay, thenpaplay/aplay.Interfaces: a CLI, an MCP stdio server, and an optional global hotkey service.
No API keys, GPU, paid service, or cloud account.
Contents
Related MCP server: Voice MCP Server
What you get
Piece | What it does | Needs the agent open? |
| Speak text from the CLI, a file, or stdin | no |
MCP server |
| yes |
Double-tap Ctrl service | Speak the selection or stop, in any app | no |
The hotkey service and the MCP server are independent. Closing the agent does not break the hotkey. Stopping the hotkey service does not break chat speech.
Requirements
Linux with working audio output. Tested on Debian/Kali-style Linux and WSL.
Python 3.10–3.13. Python 3.14 is not supported by the pinned piper/onnxruntime stack.
One playback program:
mpv(preferred),ffplay(from FFmpeg),paplay, oraplay.Network access for the first install and for
edge-tts. The piper fallback works offline after the voice model is installed.
Optional, only for the double-tap Ctrl service:
systemduser services, available on any modern desktop Linux.Membership in the
inputgroup, so the service can read/dev/input.wl-clipboardon Wayland, orxclipon X11, to read the selected or copied text. On Wayland,wl-clipboardis strongly recommended: X11 tools cannot see selections made in native Wayland apps.
install.sh never runs sudo. If a system package is missing, it prints the
apt command for you to run yourself.
Install
Option 1: clone and install
git clone https://github.com/rishb0/voice-for-agent.git
cd voice-for-agent
bash install.shOption 2: install into a stable data folder
TARGET="${XDG_DATA_HOME:-$HOME/.local/share}/voice-for-agent"
if [ -d "$TARGET/.git" ]; then
git -C "$TARGET" pull --ff-only
else
git clone --depth 1 https://github.com/rishb0/voice-for-agent.git "$TARGET"
fi
cd "$TARGET"
bash install.shOption 3: one-command bootstrap
bash bootstrap.sh \
--repo https://github.com/rishb0/voice-for-agent.git \
--register-opencodeAdd --with-service to install the double-tap Ctrl service in the same run:
bash bootstrap.sh \
--repo https://github.com/rishb0/voice-for-agent.git \
--with-serviceInstall with the hotkey service in one step
bash install.sh --with-serviceThis runs the normal install and then installs and enables the double-tap Ctrl user service. Without the flag, the service is not touched.
What install.sh does
Finds a supported Python 3.10–3.13 and checks
python3-venv.Checks for an audio player:
mpv,ffplay,paplay, oraplay.Creates a local
.venv/if needed.Installs the pinned packages from
requirements.txtinto.venv/.Reads
piper_voicefromconfig.jsonif present; otherwise usesen_US-ljspeech-high.Downloads the piper
.onnxmodel and.onnx.jsonconfig intovoices/.Runs the smoke tests.
With
--with-service, installs and enablesvoice-for-agent-hotkey.service.Exits non-zero if a required step fails.
It is idempotent: running it again repairs the install. It does not run sudo,
install system packages, or change the system Python.
If python3-venv or an audio player is missing, install it and rerun:
sudo apt update && sudo apt install -y python3 python3-venv mpv ffmpegFirst check
bash menu.sh statusThis checks the virtualenv, packages, piper voice model, audio player, config
file, MCP import, input group membership, and the hotkey service state.
Speak one sentence:
bash menu.sh speak "Build finished. All tests passed."Stop it:
bash menu.sh stopSpeak from the command line
bash menu.sh speak "Deployment finished. Two tests failed." # wait until done
bash menu.sh async "Deployment finished." # return immediately
bash menu.sh stop # stop and clear queue
bash menu.sh speaking # is it talking?
bash menu.sh log # recent activityDirectly, without the wrapper:
./.venv/bin/python speak.py "Deployment finished."
./.venv/bin/python speak.py --async "Deployment finished."
./.venv/bin/python speak.py stopRead from a file or stdin:
./.venv/bin/python speak.py --file notes.md
./.venv/bin/python speak.py --file - < notes.md
cat notes.md | ./.venv/bin/python speak.pySpeak text you selected or copied, without sending a chat message:
bash menu.sh speak-selection # highlight text, then run this
bash menu.sh speak-clipboard # copy text, then run this
bash menu.sh toggle # stop if speaking, else speak selectionspeak-selection reads the primary selection and falls back to the clipboard.
Some apps, especially terminal UIs, copy the selection to the clipboard instead
of the primary selection; in that case the clipboard is used automatically.
On Wayland, install wl-clipboard so selections from native Wayland apps are
readable:
sudo apt install -y wl-clipboardIf the hotkey keeps speaking old text, force one source in config.json:
{ "selection_source": "clipboard" }Double-tap Ctrl service
This is a small background service that reads Ctrl presses from /dev/input.
It does not use GNOME custom shortcuts, which are unreliable on Wayland.
Install it once:
bash menu.sh service installUse it:
tap
Ctrltwice quickly → speak the selection, or the clipboard if nothing is selected;tap
Ctrltwice again while speaking → stop.
The service starts at login and runs for your whole desktop session. It never
stores keystrokes. It only measures Ctrl press and release timing, and it ignores
any tap where another key was pressed while Ctrl was held, so Ctrl+C,
Ctrl+V, and Ctrl+Z never trigger it.
Reading /dev/input requires the input group:
sudo usermod -aG input "$USER"Log out and back in afterwards, then check:
id -nG | tr ' ' '\n' | grep -x inputUsing the service with systemctl
The service is a normal systemd user unit named
voice-for-agent-hotkey.service. After installing it once, control it directly
with systemctl. You do not need menu.sh for daily use.
# state
systemctl --user status voice-for-agent-hotkey.service
# start and stop on demand
systemctl --user start voice-for-agent-hotkey.service
systemctl --user stop voice-for-agent-hotkey.service
# apply a change
systemctl --user restart voice-for-agent-hotkey.service
# login behaviour
systemctl --user enable voice-for-agent-hotkey.service # start at login
systemctl --user disable voice-for-agent-hotkey.service # do not start at login
# logs
journalctl --user -u voice-for-agent-hotkey.service -n 50 --no-pager
journalctl --user -u voice-for-agent-hotkey.service -fShort forms work too:
systemctl --user restart voice-for-agent-hotkey
journalctl --user -u voice-for-agent-hotkey -fNotifications
The service shows one desktop notification when it starts. It does not notify when it stops, because a "stopped" notice would also fire on every failed restart and turn a crash loop into a stream of notifications. Speaking shows no notification at all.
If the service cannot start, it retries five times in a minute and then gives
up instead of looping forever. Run bash menu.sh status to see whether the
installed unit still points at this folder.
The only other notifications are errors, such as "nothing selected or copied", because otherwise the hotkey looks broken when there is nothing to read.
Where the unit lives
${XDG_CONFIG_HOME:-$HOME/.config}/systemd/user/voice-for-agent-hotkey.serviceIt is generated from systemd/voice-for-agent-hotkey.service.in so the unit
points at your install folder and a system Python. Reinstalling regenerates it:
bash menu.sh service install # render unit, reload, enable, startRemove the service
bash menu.sh service removeThat stops it, disables it, deletes the unit, and reloads systemd. bash uninstall.sh does the same as part of a full removal.
menu.sh service wrappers
These are thin wrappers around systemctl if you prefer them:
bash menu.sh service install # same as hotkey install
bash menu.sh service start
bash menu.sh service stop
bash menu.sh service restart
bash menu.sh service status
bash menu.sh service enable
bash menu.sh service disable
bash menu.sh service logs # journal for the unit
bash menu.sh service removeRun the daemon in the foreground for debugging:
bash menu.sh hotkey runVoices
The default configuration speaks Hinglish and English with Indian voices, and picks the voice from the script of each chunk:
Text | Voice | Notes |
Latin script, e.g. |
| Indian English male, reads Hinglish naturally |
Devanagari, e.g. |
| Hindi male |
Mixed text that contains Devanagari uses the Hindi voice. auto_voice in
config.json controls this. Passing --voice explicitly turns auto-selection
off for that call.
./.venv/bin/python speak.py --voice en-IN-PrabhatNeural "Bhai, test pass ho gaya."
./.venv/bin/python speak.py --voice-hi hi-IN-MadhurNeural "नमस्ते, सब ठीक है।"
./.venv/bin/python speak.py --no-auto-voice "Force the main voice."These are synthetic neural voices. They are not a clone of any real person.
List available voices
./.venv/bin/python speak.py --list-voices
bash menu.sh voicesThis lists edge-tts voices when online and every installed piper model in
voices/. The default piper voice is marked default.
Useful edge-tts voices:
Voice | Language | Gender |
| Indian English | male |
| Indian English | female |
| Hindi | male |
| Hindi | female |
| US English | female |
Change the voice
Edit config.json:
bash menu.sh config editThen speak again. No reinstall is needed; every new job reads the config.
Configuration
Create config.json from the example:
cp config.example.json config.json{
"engine": "edge",
"voice": "en-IN-PrabhatNeural",
"voice_hi": "hi-IN-MadhurNeural",
"auto_voice": true,
"selection_source": "auto",
"piper_voice": "en_US-ljspeech-high",
"rate": "-5%",
"pitch": "-8Hz",
"max_spoken_chars": 1200
}Key | Type | Meaning |
|
|
|
| string | edge-tts voice for Latin-script text. |
| string | edge-tts voice for Devanagari text. |
| boolean | Pick |
| string |
|
| string | Installed piper model name, without |
| string |
|
| string |
|
| number | Spoken character limit before "the rest is on screen". |
Precedence is: command-line option, then config.json, then built-in defaults.
config.json is ignored by git, so your local voice and tone stay private.
piper_voice is the stem of an .onnx file in voices/. The installer reads
this value and downloads that voice if it is missing. To add a voice later:
./.venv/bin/python -m piper.download_voices en_US-ljspeech-high --data-dir voicesCheck the voice's MODEL_CARD before using it commercially. Several Piper
voices have non-commercial or research-only terms.
CLI reference
Speak text
./.venv/bin/python speak.py "Deployment finished. Two tests failed."The default engine is edge. If edge-tts fails, for example with no network,
the tool logs one line and falls back to piper automatically.
Clean text without speaking
./.venv/bin/python speak.py --clean-only --file notes.mdThe cleaner removes fenced code blocks, markdown marks, URLs, file paths, hashes, tables, emoji, and ANSI escapes. It keeps the readable words.
Synthesize to a file instead of playing
./.venv/bin/python speak.py --engine edge --output speech.mp3 "Hello."
./.venv/bin/python speak.py --engine piper --output speech.wav "Hello."The output container follows the engine: edge writes MP3, piper writes WAV. If
you pass a different extension it is corrected, and the actual path is printed.
If edge-tts falls back to piper, the actual .wav path is printed.
Choose an engine, voice, rate, or pitch
./.venv/bin/python speak.py --engine piper --piper-voice en_US-ljspeech-high "Offline speech."
./.venv/bin/python speak.py --engine edge --voice en-IN-PrabhatNeural --rate +10% "Faster speech."
./.venv/bin/python speak.py --rate -5% "Slower speech."
./.venv/bin/python speak.py --pitch -8Hz "Deeper speech."Options
Option | Meaning |
| Text to speak. |
| Read text from a file. Use |
| Queue speech and return immediately. |
| Force one synthesis engine. |
| edge-tts voice for Latin-script text. |
| edge-tts voice for Devanagari text. |
| Pick the Hindi voice automatically for Devanagari. |
| Installed piper voice name (file stem). |
| Speech rate adjustment. |
| Speech pitch adjustment in hertz. |
| Maximum characters spoken before "the rest is on screen". |
| Synthesize to a file instead of playing. |
| Print cleaned text and exit. |
| List edge-tts and installed piper voices. |
| Print |
| Stop current speech and invalidate every queued job. |
Negative values are accepted as separate arguments: --rate -5%, --pitch -8Hz.
MCP server
The MCP server exposes two tools:
speak(text)— queue a short spoken summary and return"queued"immediately.stop_speaking()— stop current speech and clear every queued job.
The server speaks with the same config.json as the CLI. It uses stdio, so it
does not open a network port.
OpenCode
opencode mcp add voice-for-agent -- \
"$PWD/.venv/bin/python" "$PWD/mcp_server.py"Or use the manual V2 configuration in examples/opencode.jsonc:
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"servers": {
"voice-for-agent": {
"type": "local",
"command": [
"/ABSOLUTE/PATH/TO/voice-for-agent/.venv/bin/python",
"/ABSOLUTE/PATH/TO/voice-for-agent/mcp_server.py"
],
"codemode": false
}
}
}
}Claude Code
claude mcp add --scope user voice-for-agent -- \
"$PWD/.venv/bin/python" "$PWD/mcp_server.py"The same command is in examples/claude-code.sh.
Gemini CLI
Use the mcpServers block in examples/gemini-settings.json. Replace
/ABSOLUTE/PATH/TO/voice-for-agent with this folder's absolute path.
Tool names
The server name is voice-for-agent. Some clients prefix tool names, so the
tools may appear as voice-for-agent_speak and
voice-for-agent_stop_speaking. The underlying names are speak and
stop_speaking.
Agent rules and skill
File | Purpose |
| Pasteable rules: when and how the agent should speak. |
| Operations guide: install, service, status, tests, config, safety. |
| Portable skill entry point for any agent given this repository URL. |
| OpenCode-discoverable skill. |
AGENTS.md tells the agent to:
stay silent by default;
speak when the user says "speak", "read aloud", "say it", or "voice this";
speak after every answer only after the user says "voice on";
keep the spoken summary to 2–4 plain sentences;
avoid reading code, commands, paths, or long lists aloud;
call
stop_speakingwhen the user says "stop talking", "mute", or "voice off".
The full answer stays on screen. Only the short summary is spoken. Check the
current audio state with bash menu.sh speaking.
Update
cd /path/to/voice-for-agent
git pull --ff-only
bash install.sh
bash menu.sh service install # only if the unit or service changed
bash menu.sh statusWith the bootstrap install folder:
cd "${XDG_DATA_HOME:-$HOME/.local/share}/voice-for-agent"
git pull --ff-only
bash install.shconfig.json, voices/, and .run/ are untouched by git pull.
Uninstall
Preview what will be removed:
bash uninstall.sh --dry-runRemove with a confirmation prompt:
bash uninstall.shRemove without prompting, for an agent after the user confirms:
bash uninstall.sh --yesKeep downloaded voices and local config:
bash uninstall.sh --yes --keep-voices --keep-configuninstall.sh removes:
.venv/voices/(unless--keep-voices).run/.tmp/config.json(unless--keep-config)__pycache__/and*.pycthe
voice-for-agent-hotkey.serviceuser unit, if installed
It never removes source files, documentation, examples, tests, LICENSE, or
THIRD_PARTY_NOTICES.md.
After a full uninstall, remove the MCP registration from your agent client, and
optionally leave the input group:
sudo gpasswd -d "$USER" inputFiles and layout
Path | What it is |
| Single entry point: interactive menu and all commands. |
| CLI, text cleaner, chunker, synthesis, playback, queue, stop. |
| Thin FastMCP stdio wrapper exposing |
| Double-tap Ctrl daemon that reads |
| Unit template, rendered on install. |
| Idempotent setup and self-test. Never uses |
| Removes generated files, config, voices, and the user unit. |
| Clone or update from a Git URL, install, optionally register OpenCode. |
| Pinned Python dependencies. |
| Example local configuration. |
| Pasteable speaking rules for agents. |
| Operations guide for agents. |
| Portable agent-skill entry point. |
| OpenCode-discoverable skill. |
| Registration snippets for OpenCode, Claude Code, Gemini CLI. |
| End-to-end tests. |
| Double-tap Ctrl detector unit tests. |
| Voice selection, rate, and pitch unit tests. |
| Primary selection vs clipboard decision tests. |
| CI: syntax checks and unit tests. |
| MIT License for this project. |
| Dependency and voice-model license notes. |
| Generated locally, ignored by git. |
Everything persistent stays inside the install folder, except the optional user
unit in ~/.config/systemd/user/.
Path | Approximate size | Purpose |
| about 270 MB | Local Python environment and packages. |
| 109 MB for the default voice | Downloaded piper model and config. |
| small | Locks, generation counter, log. |
| small | Temporary audio, deleted after playback. |
| small | Optional local configuration. |
du -sh .venv voices .run .tmp 2>/dev/nullPip caching is disabled with --no-cache-dir, so no persistent package cache is
kept in ~/.cache/pip.
Tests
bash menu.sh testor directly:
bash tests/smoke_test.shThe smoke test checks:
edge-tts produces audio (requires network);
piper produces audio offline;
the text cleaner removes markdown, URLs, code, paths, hashes, tables, emoji;
the MCP server starts and lists
speakandstop_speaking;real playback works, or an audio-file fallback passes with no audio device;
the double-tap Ctrl detector unit tests;
voice selection, rate, and pitch unit tests;
primary selection vs clipboard decision tests.
install.sh runs the same suite at the end.
Troubleshooting
Start here:
bash menu.sh status
bash menu.sh log
systemctl --user status voice-for-agent-hotkey.serviceService problems
Unit voice-for-agent-hotkey.service could not be found — the unit is not
installed. Run bash menu.sh service install.
Service is active but double-tap Ctrl does nothing — check group access and
the log:
id -nG | tr ' ' '\n' | grep -x input
bash menu.sh log 20
journalctl --user -u voice-for-agent-hotkey.service -n 30 --no-pagerThe log line hotkey: watching N input device(s) means it found keyboards. If it
says no readable /dev/input devices, add yourself to the input group and log
out and back in.
Double-tap works, but nothing is spoken — the selection may be empty. The
daemon falls back to the clipboard. Check that xclip or wl-clipboard is
installed, and look at .run/speak.log for speak-selection lines.
Double-tap speaks old text — the app put the new selection in the clipboard
while the X11 primary selection stayed stale. Install wl-clipboard on Wayland,
or set "selection_source": "clipboard" in config.json. The log line
speak-selection: N chars via ... (mode=...) shows which source was used.
Service dies after a crash — Restart=on-failure with RestartSec=5 brings
it back automatically. Confirm with systemctl --user status.
Service does not start at login — enable it:
systemctl --user enable voice-for-agent-hotkey.serviceSpeech problems
edge-tts failed, falling back to piper — edge-tts needs network access.
Piper still works offline. To force local speech, use --engine piper.
piper voice model missing — the selected piper_voice is not installed.
Run bash install.sh, or download it with
./.venv/bin/python -m piper.download_voices NAME --data-dir voices.
no audio player found — install mpv or FFmpeg:
sudo apt update && sudo apt install -y mpv ffmpegplayback failed — the player exists but cannot reach an audio device.
Check desktop audio, PipeWire/PulseAudio, or WSL audio. Run ffplay manually to
see the error.
No sound but no error — synthesize a file and play it with your normal player:
./.venv/bin/python speak.py --engine piper --output test.wav "test"nothing to speak — the input was empty, or the cleaner removed everything
(code blocks and URLs only). Check with --clean-only.
Wrong language voice — Devanagari uses voice_hi; Latin script uses voice.
Set auto_voice to false to always use voice.
Agent and MCP problems
MCP client does not show the tools — use absolute paths to
.venv/bin/python and mcp_server.py, then run the command manually to see
startup errors. The server must run where mcp is installed, which is .venv/.
install.sh cannot find a supported Python — install Python 3.11 or 3.12
and python3-venv. Python 3.14 is intentionally rejected by the piper stack.
A queued job will not stop — run ./.venv/bin/python speak.py stop. If a
stale process remains, inspect it with ps -ef | grep speak.py before killing
anything.
Platform support
Linux: supported.
WSL: supported; audio depends on the WSL audio setup. systemd user services need systemd enabled in WSL.
macOS: not supported by the current installer or player list. The Python code uses Unix features, but
install.shis Debian/apt-specific and there is noafplaysupport yet.Native Windows: not supported.
speak.pyusesfcntland Unix process groups for queueing and stop. Use WSL instead.
Privacy and security
edge-tts sends the text to Microsoft. Do not send secrets or private data through the edge engine.
piper runs locally. Use
--engine piperwhen the text must stay on the machine.There are no API keys, accounts, telemetry, or network listeners.
The MCP server uses stdio only.
The hotkey service reads
/dev/inputbut stores no keystrokes. It keeps only Ctrl press and release timing in memory and never writes key data to disk.Text is passed to subprocesses as argument lists, not through a shell.
--filereads any path the current user can read; treat it like any other file-reading CLI.Async errors go to
.run/speak.log. Temporary audio is deleted after each chunk and bystop.
Limits
Output only: no microphone, no speech-to-text, no realtime duplex chat.
edge-tts needs internet; piper is offline but less expressive.
Long text is truncated for speech, not summarized. The agent's full answer stays on screen.
Speech is serialized. A second job waits for the first unless you call
stop.One piper voice is installed by default. Add more with the download command.
The hotkey service needs
systemduser units andinputgroup access.No native Windows or macOS installer is included. WSL/Linux is the tested path.
Voice models and licensing
The default piper voice is en_US-ljspeech-high:
trained from scratch on the LJ Speech dataset;
dataset license: public domain;
model card: https://huggingface.co/rhasspy/piper-voices/raw/main/en/en_US/ljspeech/high/MODEL_CARD.
The model files are downloaded by install.sh and are ignored by git. They are
not part of this repository.
Piper voice licensing is inconsistent. Many English voices are fine-tuned from
the Lessac voice and carry research-only or non-commercial terms. The older
en_US-lessac-medium voice, for example, uses the Blizzard 2013 research
license and is not suitable for commercial use. Check the MODEL_CARD of any
voice you redistribute or use commercially.
Edge-tts voices are provided by Microsoft under its terms of service.
This project's own code is licensed under the MIT License. It uses
third-party dependencies under their own terms: edge-tts is LGPL-3.0,
piper-tts is GPL-3.0-or-later, and mcp and onnxruntime are MIT. See
LICENSE and THIRD_PARTY_NOTICES.md.
If you redistribute a combined package that includes piper-tts, follow the
GPL-3.0-or-later terms for that combined distribution.
Repository hygiene
Generated and private files are ignored by git:
.venv/— local Python environment;voices/*.onnxandvoices/*.onnx.json— downloaded voice models;.run/and.tmp/— runtime state and temporary audio;config.json— local configuration;__pycache__/,*.pyc, audio files, and logs.
Before publishing, run git status and confirm none of those appear. The
example registration files use /ABSOLUTE/PATH/TO/voice-for-agent placeholders.
Publish to GitHub
Create an empty public repository named voice-for-agent on GitHub. From a
fresh copy of this folder:
git init
git add .
git commit -m "Initial public release"
git branch -M main
git remote add origin https://github.com/rishb0/voice-for-agent.git
git push -u origin mainConfirm git status does not show .venv/, voices/*.onnx, .run/, .tmp/,
or config.json.
The documentation uses rishb0 as the publishing account. If you push to a
different account or organization, replace rishb0 in README.md, SKILL.md,
AGENT_GUIDE.md, bootstrap.sh, and the .opencode skill. Set the repository
visibility to public, enable Issues, and add topics such as text-to-speech,
tts, mcp, opencode, piper, and edge-tts.
The GitHub Actions workflow runs syntax checks and the unit tests on every push and pull request. It does not need network, audio hardware, or the piper voice model.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Audio for your agent: transcribe, speak, translate, summarise, plus sound effects and music.
Text to speech for your AI. Your AI can send text to Doc Player to read it aloud. You will see a reader window with the text and you can control the playback sentence by sentence. Find an example here: https://documentplayer.com/connect-ai/
Let cloud agents talk to you: progress updates spoken on your Mac, and replies you send back.
Ask other AI models and generate images, speech, music and video from your coding agent.
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables AI agents to synthesize natural speech using either platform system voices or premium OpenAI TTS, with automatic engine selection and graceful fallback.19 npmMIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to speak aloud by generating and playing audio through the system output. Supports multiple TTS providers, playback queue management, and configurable voice profiles.1MIT
- AlicenseAqualityBmaintenanceEnables an AI assistant to have its recent code actions summarized aloud through system speakers, using offline native voices or cloud neural voices. It supports asynchronous playback and voice listing so users can hear what the agent did without reading the full response.335 PyPIMIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to give spoken output by synthesizing text into speech with an on-device neural model and playing it through the user's speakers, entirely offline. Agents can queue spoken summaries and stop playback on demand.4 npmMIT