Voice Mode - Mibyan Docs

Mibyan supports full voice interaction across CLI and messaging platforms. Talk to the agent using your microphone, hear spoken replies, and have live voice conversations in Discord voice channels. If you want a practical setup walkthrough with recommended configurations and real usage patterns, see Use Voice Mode with Mibyan. For hands-free session start — saying “hey mibyan” (or any phrase) to open a fresh voice session on the CLI, TUI, or desktop app — see Wake Word.

Prerequisites

Before using voice features, make sure you have:

Mibyan installed — via the install script (see Installation)
An LLM provider configured — run mibyan model or set your preferred provider credentials in ~/.mibyan/.env
A working base setup — run mibyan to verify the agent responds to text before enabling voice

The ~/.mibyan/ directory and default config.yaml are created automatically the first time you run mibyan. You only need to create ~/.mibyan/.env manually for API keys.

Nous Portal covers bothA paid Nous Portal subscription supplies the LLM (step 2) and OpenAI TTS via the Tool Gateway — no separate OpenAI key needed. On a fresh install, mibyan setup --portal wires both up at once.

Overview

Feature	Platform	Description
Interactive Voice	CLI	Press Ctrl+B to record, agent auto-detects silence and responds
Auto Voice Reply	Telegram, Discord	Agent sends spoken audio alongside text responses
Voice Channel	Discord	Bot joins VC, listens to users speaking, speaks replies back

Requirements

Python Packages

Use mibyan tools to configure voice providers. Missing built-in feature requirements go through PM, subject to security.allow_lazy_installs and the target’s dependency support. Restart Mibyan if the selected dependency environment changes. A bundled app includes its supported engine dependencies. Docker includes a curated subset and disables on-demand installs. Do not use pip to modify a signed payload or the system Python. For a manual development environment, select the required extras in the development setup.

Extra	Packages	Required For
`voice`	`sounddevice`, `numpy`, and Faster-Whisper where supported	CLI audio and optional local STT
`messaging`	`discord.py[voice]`, `python-telegram-bot`, `aiohttp`	Discord & Telegram bots
`tts-premium`	`elevenlabs`	ElevenLabs TTS provider

Local Faster-Whisper is excluded on native Windows ARM64 and Intel macOS. Use a cloud or command-based STT provider on those targets. audio-io contains the microphone/playback dependencies without local STT. The all extra does not mean every voice or wake engine. NeuTTS is a separate optional runtime and downloads models on first use. Do not install its dependencies into a signed app or system Python.

discord.py[voice] installs PyNaCl (for voice encryption) and opus bindings automatically. This is required for Discord voice channel support.

System Dependencies

# macOS
brew install portaudio ffmpeg opus
brew install espeak-ng   # for NeuTTS

# Ubuntu/Debian
sudo apt install portaudio19-dev ffmpeg libopus0
sudo apt install espeak-ng   # for NeuTTS

Dependency	Purpose	Required For
PortAudio	Microphone input and audio playback	CLI voice mode
ffmpeg	Audio format conversion (MP3 → Opus, PCM → WAV)	All platforms
Opus	Discord voice codec	Discord voice channels
espeak-ng	Phonemizer backend	Local NeuTTS provider

API Keys

Add to ~/.mibyan/.env:

# Speech-to-Text — local provider needs NO key at all
# PM prepares local Faster-Whisper on supported targets; no STT API key is needed.
GROQ_API_KEY=your-key                 # Groq Whisper — fast, free tier (cloud)
VOICE_TOOLS_OPENAI_KEY=your-key       # OpenAI Whisper — paid (cloud)

# Text-to-Speech (optional — Edge TTS and NeuTTS work without any key)
ELEVENLABS_API_KEY=***           # ElevenLabs — premium quality
# VOICE_TOOLS_OPENAI_KEY above also enables OpenAI TTS

If faster-whisper is installed, voice mode works with zero API keys for STT. The model (~150 MB for base) downloads automatically on first use.

The first download normally comes from huggingface.co. If that host is unavailable on your network, export an accessible mirror in the shell or service that starts Mibyan:

HF_ENDPOINT=https://your-hugging-face-mirror.example
HF_HUB_DISABLE_XET=1

Disabling Xet avoids authentication failures from Xet’s separate CAS hosts when a mirror is in use. After the model is cached, Mibyan loads that snapshot without an online revision check.

CLI Voice Mode

Voice mode is available in both the classic CLI (mibyan chat) and the TUI (mibyan --tui). Behavior is identical across both — same slash commands, same VAD silence detection, same streaming TTS, same hallucination filter. The TUI additionally forwards crash-forensic logs to ~/.mibyan/logs/ so push-to-talk failures on exotic audio backends can be reported with a full stack trace rather than disappearing silently.

Quick Start

Start the CLI and enable voice mode:

mibyan                # Start the interactive CLI

Then use these commands inside the CLI:

/voice          Toggle voice mode on/off
/voice on       Enable voice mode
/voice off      Disable voice mode
/voice tts      Toggle TTS output
/voice status   Show current state

How It Works

Start the CLI with mibyan and enable voice mode with /voice on
Press Ctrl+B — a beep plays (880Hz), recording starts
Speak — a live audio level bar shows your input: ● [▁▂▃▅▇▇▅▂] ❯
Stop speaking — after 3 seconds of silence, recording auto-stops
Two beeps play (660Hz) confirming the recording ended
Audio is transcribed via Whisper and sent to the agent
If TTS is enabled, the agent’s reply is spoken aloud
Recording automatically restarts — speak again without pressing any key

This loop continues until you press Ctrl+B during recording (exits continuous mode) or 3 consecutive recordings detect no speech.

The record key is configurable via voice.record_key in ~/.mibyan/config.yaml (default: ctrl+b).

Silence Detection

Two-stage algorithm detects when you’ve finished speaking:

Speech confirmation — waits for audio above the RMS threshold (200) for at least 0.3s, tolerating brief dips between syllables
End detection — once speech is confirmed, triggers after 3.0 seconds of continuous silence

If no speech is detected at all for 15 seconds, recording stops automatically. Both silence_threshold and silence_duration are configurable in config.yaml. You can also disable the record start/stop beeps with voice.beep_enabled: false.

Ending a voice chat by voice

Say “stop” — and nothing else — to end the voice conversation hands-free. The match is deliberately strict: the whole utterance (case-insensitive, surrounding punctuation ignored) must equal a configured phrase, so “stop doing that and try X instead” still reaches the agent normally. Customize the phrase list with voice.stop_phrases in config.yaml (e.g. ["stop", "goodbye mibyan"]), or set it to [] to disable. Phrases can be in any language (e.g. ["отбой", "стоп"] with stt.language: ru). The desktop app honours the same list; while voice.stop_phrases is left at its default it also accepts a few English extras (“goodbye”, “never mind”, “cancel”, …), and a customised list replaces them. A voice chat also ends on its own after three consecutive silent cycles (no speech detected). Typing a bare stop phrase while a voice chat is active works the same way on every surface (CLI, TUI, desktop): the message ends the voice chat instead of being sent to the agent. Outside a voice chat, typed “stop” is an ordinary message.

Streaming TTS

When TTS is enabled, the agent speaks its reply sentence-by-sentence as it generates text — you don’t wait for the full response. This works with every TTS provider:

Buffers text deltas into complete sentences (min 20 chars)
Strips markdown formatting, emoji, and <think> blocks
Plays audio per sentence in real-time — providers with a chunked PCM API (ElevenLabs, OpenAI) stream raw audio for the lowest time-to-first-word; every other provider (including the default Edge) synthesizes and plays each sentence as it completes

The same pipeline runs in the classic CLI, the TUI, and the desktop app. In a desktop voice conversation the reply text is fed live into a per-reply speech WebSocket as the model generates it, so speech overlaps generation — one socket and one audio clock per reply, no per-sentence connection gaps.

Desktop remote: client-direct voice (lowest-hop path)

When Mibyan Desktop is connected to a remote gateway, audio does not need to be relayed through the gateway at all. At voice-session start the desktop fetches the active profile’s resolved STT/TTS settings (provider, model, language/voice, and credential) from the gateway over the authenticated REST channel (GET /api/audio/voice-config) and then calls the providers directly:

Dictation / voice input: the mic recording goes straight from your desktop to the profile’s STT provider; only the resulting text is sent to the gateway as the prompt.
Spoken replies: the reply text is already streaming to the desktop over the chat socket, so the desktop synthesizes it locally with the profile’s TTS provider and plays it — the gateway link never carries audio.

There is nothing to configure on the client: the profile you’re talking to is the single source of truth for providers and keys, exactly as if the gateway had done the work itself. Keys are held in the desktop’s memory for the session only — never written to disk on the client. Providers that can only run on the gateway host (local whisper, edge TTS, command providers, plugins) automatically fall back to the relay path (/api/audio/transcribe and the speech WebSocket), as does any older backend without the endpoint. To force the relay for every provider, set:

voice:
  client_direct: false

Client-direct wire support: OpenAI (incl. Nous-managed audio), Groq, Mistral, and DeepInfra via the OpenAI-compatible shapes, xAI Grok STT, and ElevenLabs STT + TTS. xAI configured through OAuth stays on the relay (the OAuth bearer refreshes server-side).

Desktop: GPT-Live voice chat mode (full duplex, delegates to Mibyan)

The chained loop above is one of two voice chat modes in the desktop app. The other replaces the whole STT → turn → TTS chain with one full-duplex voice model, OpenAI’s gpt-live-1: it listens while it speaks, handles interruptions, backchannels and background noise itself, and has no tools of its own. Whenever you ask for real work it delegates to Mibyan, which answers as usual — with whatever model and provider the session has selected, the full toolset, memory and approvals — and the voice paraphrases the answer aloud.

voice:
  voice_chat_mode: gpt-live     # chained (default) | gpt-live
  gpt_live:
    voice: marin                # marin, cedar, quartz, ripple, vesper, willow, stone, gleam, meridian, …
    instructions: ""            # optional extra persona sentences (tone, pace, language)

Requirements: an OpenAI API key (OPENAI_API_KEY, VOICE_TOOLS_OPENAI_KEY, or voice.gpt_live.api_key). The voice layer is billed by OpenAI at $0.05 per minute of session time (idle time counts); the Mibyan turn is billed on its own provider as always. The mode is also in Settings → Voice → Voice Chat Mode. How it works: pressing the voice button opens a WebRTC session from the desktop to GPT-Live; the desktop only ever receives a session id and an SDP answer — the key stays on the gateway host, which performs the session creation (POST /api/audio/voice-live/session). Each session.delegation.created becomes a normal turn on the open chat (the bubble shows what you said; the recent spoken exchange rides the model input as a per-turn note, never the system prompt, so the reply is speakable prose). Tool activity is fed to the voice as quiet context (“Mibyan is working: terminal”) so it can tell you what is happening if you ask; the final answer is streamed back sentence by sentence. Saying the stop phrase ends the conversation. If gpt-live is selected but no key resolves, the button falls back to the chained mode with a notice. Not supported in this mode: the Nous-managed audio proxy (direct key only), the CLI/TUI (/voice keeps the chained loop), and the tts tool (it keeps using tts.provider).

Barge-in

You can interrupt the agent at ANY point in its turn — the microphone stays live from the moment you finish speaking until the reply has fully played (full duplex):

Interject while it’s thinking — in continuous voice mode, speaking during LLM generation (before any audio plays) interrupts the in-flight turn and your interjection becomes the next message, the same as typing over a running turn.
Talk over it — speaking while the agent’s reply plays cuts playback the moment you start talking and submits what you said. The detector calibrates its noise floor against the quiet room at turn start (never against the playback itself), so speaker bleed can’t deafen it and normal speech reliably trips it.
Type or press the record key — sending a new message or hitting the push-to-talk key stops playback instantly on every surface.
Say “stop” — the stop phrase works in both phases: mid-generation it interrupts the turn AND ends the voice chat; mid-playback it cuts the speech and ends the chat.

Tuning (config.yaml): voice.barge_in: false disables it; voice.barge_in_threshold_multiplier (default 3.0) scales the speech trigger over the quiet-room floor — lower is more sensitive; the desktop app also scales its playback-phase trigger by it, so a quiet Bluetooth headset that can’t interrupt a reply can use e.g. 1.5; voice.barge_in_grace_seconds (default 0.5) suppresses trips right after playback starts. Set mibyan_VOICE_DEBUG=1 to stream per-block VAD diagnostics (calibrated floor, RMS, trip decisions) to stderr for live tuning. The agent knows it was interrupted: the next message carries a short note telling the model its spoken reply was cut off, so it can react naturally (“rude!”) or pick up where it left off instead of being oblivious.

Hallucination Filter

Whisper sometimes generates phantom text from silence or background noise (“Thank you for watching”, “Subscribe”, etc.). The agent filters these out using a set of 26 known hallucination phrases across multiple languages, plus a regex pattern that catches repetitive variations.

Gateway Voice Reply (Telegram & Discord)

If you haven’t set up your messaging bots yet, see the platform-specific guides:

Start the gateway to connect to your messaging platforms:

mibyan gateway        # Start the gateway (connects to configured platforms)
mibyan gateway setup  # Interactive setup wizard for first-time configuration

Discord: Channels vs DMs

The bot supports two interaction modes on Discord:

Mode	How to Talk	Mention Required	Setup
Direct Message (DM)	Open the bot’s profile → “Message”	No	Works immediately
Server Channel	Type in a text channel where the bot is present	Yes (`@botname`)	Bot must be invited to the server

DM (recommended for personal use): Just open a DM with the bot and type — no @mention needed. Voice replies and all commands work the same as in channels. Server channels: The bot only responds when you @mention it (e.g. @mibyanbyt4 hello). Make sure you select the bot user from the mention popup, not the role with the same name.

To disable the mention requirement in server channels, add to ~/.mibyan/.env:

DISCORD_REQUIRE_MENTION=false

Or set specific channels as free-response (no mention needed):

DISCORD_FREE_RESPONSE_CHANNELS=123456789,987654321

Commands

These work in both Telegram and Discord (DMs and text channels):

/voice          Toggle voice mode on/off
/voice on       Voice replies only when you send a voice message
/voice tts      Voice replies for ALL messages
/voice off      Disable voice replies
/voice status   Show current setting

Modes

Mode	Command	Behavior
`off`	`/voice off`	Text only (default)
`voice_only`	`/voice on`	Speaks reply only when you send a voice message
`all`	`/voice tts`	Speaks reply to every message

Voice mode setting is persisted across gateway restarts.

Platform Delivery

Platform	Format	Notes
Telegram	Voice bubble (Opus/OGG)	Plays inline in chat. ffmpeg converts MP3 → Opus if needed
Discord	Native voice bubble (Opus/OGG)	Plays inline like a user voice message. Falls back to file attachment if voice bubble API fails

Discord Voice Channels

The most immersive voice feature: the bot joins a Discord voice channel, listens to users speaking, transcribes their speech, processes through the agent, and speaks the reply back in the voice channel.

Setup

1. Discord Bot Permissions

If you already have a Discord bot set up for text (see Discord Setup Guide), you need to add voice permissions. Go to the Discord Developer Portal → your application → Installation → Default Install Settings → Guild Install: Add these permissions to the existing text permissions:

Permission	Purpose	Required
Connect	Join voice channels	Yes
Speak	Play TTS audio in voice channels	Yes
Use Voice Activity	Detect when users are speaking	Recommended

Updated Permissions Integer:

Level	Integer	What’s Included
Text only	`309237763136`	View Channels, Send Messages, Read History, Embeds, Attachments, Threads, Reactions, Create Public Threads
Text + Voice	`309240908864`	All above + Connect, Speak

Re-invite the bot with the updated permissions URL:

https://discord.com/oauth2/authorize?client_id=YOUR_APP_ID&scope=bot+applications.commands&permissions=309240908864

Replace YOUR_APP_ID with your Application ID from the Developer Portal.

Re-inviting the bot to a server it’s already in will update its permissions without removing it. You won’t lose any data or configuration.

2. Privileged Gateway Intents

In the Developer Portal → your application → Bot → Privileged Gateway Intents, enable all three:

Intent	Purpose
Presence Intent	Detect user online/offline status
Server Members Intent	Resolve usernames in `DISCORD_ALLOWED_USERS` to numeric IDs (conditional)
Message Content Intent	Read text message content in channels

Message Content Intent is required. Server Members Intent is only needed if your DISCORD_ALLOWED_USERS list uses usernames — if you use numeric user IDs, you can leave it OFF. Voice-channel SSRC → user_id mapping comes from Discord’s SPEAKING opcode on the voice websocket and does not require the Server Members Intent.

3. Opus Codec

The Opus codec library must be installed on the machine running the gateway:

# macOS (Homebrew)
brew install opus

# Ubuntu/Debian
sudo apt install libopus0

The bot auto-loads the codec from:

macOS: /opt/homebrew/lib/libopus.dylib
Linux: libopus.so.0

4. Environment Variables

# ~/.mibyan/.env

# Discord bot (already configured for text)
DISCORD_BOT_TOKEN=your-bot-token
DISCORD_ALLOWED_USERS=your-user-id

# PM prepares local Faster-Whisper on supported targets; no STT API key is needed.
# GROQ_API_KEY=your-key            # Alternative: cloud-based, fast, free tier

# TTS — optional. Edge TTS and NeuTTS need no key.
# ELEVENLABS_API_KEY=***      # Premium quality
# VOICE_TOOLS_OPENAI_KEY=***  # OpenAI TTS / Whisper

Start the Gateway

mibyan gateway        # Start with existing configuration

The bot should come online in Discord within a few seconds.

Commands

Use these in the Discord text channel where the bot is present:

/voice join      Bot joins your current voice channel
/voice channel   Alias for /voice join
/voice leave     Bot disconnects from voice channel
/voice status    Show voice mode and connected channel

You must be in a voice channel before running /voice join. The bot joins the same VC you’re in.

How It Works

When the bot joins a voice channel, it:

Listens to each user’s audio stream independently
Detects silence — 1.5s of silence after at least 0.5s of speech triggers processing
Transcribes the audio via Whisper STT (local, Groq, or OpenAI)
Processes through the full agent pipeline (session, tools, memory)
Speaks the reply back in the voice channel via TTS

Text Channel Integration

When the bot is in a voice channel:

Transcripts appear in the text channel: [Voice] @user: what you said
Agent responses are sent as text in the channel AND spoken in the VC
The text channel is the one where /voice join was issued

Echo Prevention

The bot automatically pauses its audio listener while playing TTS replies, preventing it from hearing and re-processing its own output.

Access Control

Only users listed in DISCORD_ALLOWED_USERS can interact via voice. Other users’ audio is silently ignored.

# ~/.mibyan/.env
DISCORD_ALLOWED_USERS=284102345871466496

Configuration Reference

config.yaml

# Voice recording (CLI)
voice:
  record_key: "ctrl+b"            # Key to start/stop recording
  max_recording_seconds: 120       # Maximum recording length
  auto_tts: false                  # Auto-enable TTS when voice mode starts
  beep_enabled: true               # Play record start/stop beeps
  silence_threshold: 200           # RMS level (0-32767) below which counts as silence
  silence_duration: 3.0            # Seconds of silence before auto-stop
  stop_phrases: ["stop"]           # Saying exactly one of these ends the voice chat; [] disables

# Speech-to-Text
stt:
  enabled: true                     # set to false to skip auto-transcription —
                                    # the gateway still caches the audio file and
                                    # passes its path to the agent as part of the
                                    # inbound message, useful for custom pipelines
                                    # (diarization, alignment, archival, etc.)
  provider: "local"                  # "local" (free) | "groq" | "openai" | "mistral" | "xai"
  local:
    model: "base"                    # tiny, base, small, medium, large-v3
    language: ""                     # optional ISO-639-1 hint; blank = use mibyan_LOCAL_STT_LANGUAGE if set, else auto-detect
  groq:
    language: ""                     # optional ISO-639-1 hint; blank = use mibyan_LOCAL_STT_LANGUAGE if set, else auto-detect
  # model: "whisper-1"              # Legacy: used when provider is not set

# Text-to-Speech
tts:
  provider: "edge"                 # "edge" (free) | "elevenlabs" | "openai" | "neutts" | "minimax" | "mistral" | "gemini" | "xai" | "kittentts" | "piper"
  edge:
    voice: "en-US-AriaNeural"      # 322 voices, 74 languages
  elevenlabs:
    voice_id: "pNInz6obpgDQGcFmaJgB"    # Adam
    model_id: "eleven_multilingual_v2"   # or eleven_v3, eleven_flash_v2_5, ... (Desktop Settings → Voice accepts any model id)
  openai:
    model: "gpt-4o-mini-tts"
    voice: "alloy"                 # alloy, echo, fable, onyx, nova, shimmer
    base_url: "https://api.openai.com/v1"  # optional: override for self-hosted or OpenAI-compatible endpoints
    # The `text_to_speech` tool accepts an optional per-call `instructions`
    # argument (tone, emotion, pacing, accent, whispering) that is forwarded
    # to `gpt-4o-mini-tts` and to OpenAI-compatible voice-design servers
    # (e.g. Qwen3-TTS-VoiceDesign via oMLX). See OpenAI's voice-design guide:
    # https://platform.openai.com/docs/guides/text-to-speech
  neutts:
    ref_audio: ''
    ref_text: ''
    model: neuphonic/neutts-air-q4-gguf
    device: cpu

Environment Variables

# Speech-to-Text providers (local needs no key)
# PM prepares local Faster-Whisper on supported targets; no STT API key is needed.
GROQ_API_KEY=...                    # Groq Whisper (fast, free tier)
VOICE_TOOLS_OPENAI_KEY=...         # OpenAI Whisper (paid)

# STT advanced overrides (optional)
STT_GROQ_MODEL=whisper-large-v3-turbo    # Override default Groq STT model
STT_OPENAI_MODEL=whisper-1               # Override default OpenAI STT model
GROQ_BASE_URL=https://api.groq.com/openai/v1     # Custom Groq endpoint
STT_OPENAI_BASE_URL=https://api.openai.com/v1    # Custom OpenAI STT endpoint

# Text-to-Speech providers (Edge TTS and NeuTTS need no key)
ELEVENLABS_API_KEY=***             # ElevenLabs (premium quality)
# VOICE_TOOLS_OPENAI_KEY above also enables OpenAI TTS

# Discord voice channel
DISCORD_BOT_TOKEN=...
DISCORD_ALLOWED_USERS=...

STT Provider Comparison

Provider	Model	Speed	Quality	Cost	API Key
Local	`base`	Fast (depends on CPU/GPU)	Good	Free	No
Local	`small`	Medium	Better	Free	No
Local	`large-v3`	Slow	Best	Free	No
Groq	`whisper-large-v3-turbo`	Very fast (~0.5s)	Good	Free tier	Yes
Groq	`whisper-large-v3`	Fast (~1s)	Better	Free tier	Yes
OpenAI	`whisper-1`	Fast (~1s)	Good	Paid	Yes
OpenAI	`gpt-4o-transcribe`	Medium (~2s)	Best	Paid	Yes
OpenAI	`gpt-transcribe`	Fast	Best	Paid ($0.0045/min)	Yes
Mistral	`voxtral-mini-latest`	Fast	Good	Paid	Yes
xAI	`grok-stt`	Fast	Good	Paid	Yes

Provider priority (automatic fallback): local > groq > openai

TTS Provider Comparison

Provider	Quality	Cost	Latency	Key Required
Edge TTS	Good	Free	~1s	No
ElevenLabs	Excellent	Paid	~2s	Yes
OpenAI TTS	Good	Paid	~1.5s	Yes
NeuTTS	Good	Free	Depends on CPU/GPU	No

NeuTTS uses the tts.neutts config block above. For openai, the text_to_speech tool accepts an optional instructions argument that unlocks gpt-4o-mini-tts’s voice-design capability (tone, emotion, pacing, accent, whispering). The same field also routes to OpenAI-compatible voice-design servers mounted via tts.openai.base_url (e.g. Qwen3-TTS-VoiceDesign via oMLX).

Troubleshooting

”No audio device found” (CLI)

PortAudio is not installed:

brew install portaudio    # macOS
sudo apt install portaudio19-dev  # Ubuntu

If you are running Mibyan inside Docker on a Linux desktop, the container also needs access to your host audio socket. See the Docker audio bridge notes for a PulseAudio/PipeWire-compatible setup.

Bot doesn’t respond in Discord server channels

The bot requires an @mention by default in server channels. Make sure you:

Type @ and select the bot user (with the #discriminator), not the role with the same name
Or use DMs instead — no mention needed
Or set DISCORD_REQUIRE_MENTION=false in ~/.mibyan/.env

Bot joins VC but doesn’t hear me

Check your Discord user ID is in DISCORD_ALLOWED_USERS
Make sure you’re not muted in Discord
The bot needs a SPEAKING event from Discord before it can map your audio — start speaking within a few seconds of joining

Bot hears me but doesn’t respond

Verify STT is available: install faster-whisper (no key needed) or set GROQ_API_KEY / VOICE_TOOLS_OPENAI_KEY
Check the LLM model is configured and accessible
Review gateway logs: tail -f ~/.mibyan/logs/gateway.log

Bot responds in text but not in voice channel

TTS provider may be failing — check API key and quota
Edge TTS (free, no key) is the default fallback
Check logs for TTS errors

Whisper returns garbage text

The hallucination filter catches most cases automatically. If you’re still getting phantom transcripts:

Use a quieter environment
Adjust silence_threshold in config (higher = less sensitive)
Try a different STT model

​Prerequisites

​Overview

​Requirements

​Python Packages

​System Dependencies

​API Keys

​CLI Voice Mode

​Quick Start

​How It Works

​Silence Detection

​Ending a voice chat by voice

​Streaming TTS

​Desktop remote: client-direct voice (lowest-hop path)

​Desktop: GPT-Live voice chat mode (full duplex, delegates to Mibyan)

​Barge-in

​Hallucination Filter

​Gateway Voice Reply (Telegram & Discord)

​Discord: Channels vs DMs

​Commands

​Modes

​Platform Delivery

​Discord Voice Channels

​Setup

​1. Discord Bot Permissions

​2. Privileged Gateway Intents

​3. Opus Codec

​4. Environment Variables

​Start the Gateway

​Commands

​How It Works

​Text Channel Integration

​Echo Prevention

​Access Control

​Configuration Reference

​config.yaml

​Environment Variables

​STT Provider Comparison

​TTS Provider Comparison

​Troubleshooting

​”No audio device found” (CLI)

​Bot doesn’t respond in Discord server channels

​Bot joins VC but doesn’t hear me

​Bot hears me but doesn’t respond

​Bot responds in text but not in voice channel

​Whisper returns garbage text

Prerequisites

Overview

Requirements

Python Packages

System Dependencies

API Keys

CLI Voice Mode

Quick Start

How It Works

Silence Detection

Ending a voice chat by voice

Streaming TTS

Desktop remote: client-direct voice (lowest-hop path)

Desktop: GPT-Live voice chat mode (full duplex, delegates to Mibyan)

Barge-in

Hallucination Filter

Gateway Voice Reply (Telegram & Discord)

Discord: Channels vs DMs

Commands

Modes

Platform Delivery

Discord Voice Channels

Setup

1. Discord Bot Permissions

2. Privileged Gateway Intents

3. Opus Codec

4. Environment Variables

Start the Gateway

Commands

How It Works

Text Channel Integration

Echo Prevention

Access Control

Configuration Reference

config.yaml

Environment Variables

STT Provider Comparison

TTS Provider Comparison

Troubleshooting

”No audio device found” (CLI)

Bot doesn’t respond in Discord server channels

Bot joins VC but doesn’t hear me

Bot hears me but doesn’t respond

Bot responds in text but not in voice channel

Whisper returns garbage text