STT-Assistant/config.example.toml

[audio]
backend     = "parec"
device      = "VirtualMicSink.monitor"
sample_rate = 16000
channels    = 1
frame_ms    = 30
gain        = 1.0

[vad]
aggressiveness   = 2
pre_roll_ms      = 400
speech_start_ms  = 90
silence_ms       = 700
min_utterance_ms = 300
max_utterance_s  = 30.0
chunk_pause_ms   = 350
soft_max_s       = 10.0
rms_floor        = 0.008
trailing_trim_ms = 200

[whisper]
backend                 = "faster-whisper"
model                   = "small"
device                  = "cpu"
compute_type            = "int8"
language                = "auto"
beam_size               = 1
vad_filter              = false
cpu_threads             = 0
no_speech_prob_max      = 0.6
avg_logprob_min         = -1.0
language_strategy       = "static"
sticky_redetect_logprob = -0.8

[sink]
sink_name             = "VirtualMicSink"
remap_source_name     = "VirtualMic"
loopback_latency_msec = 1
monitor_output        = false

[output]
stdout     = true
jsonl      = false
jsonl_dir  = "transcripts"
save_audio = false
audio_dir  = "audio"

[daemon]
queue_size      = 50
backlog_warn_at = 5

[events]
socket       = ""
heartbeat_ms = 1000
ring_size    = 200

[assistant]
control_socket        = ""
stall_timeout_ms      = 3000
worker_stall_ms       = 15000
command_arm_timeout_s = 10.0
chat_idle_timeout_s   = 300.0
turn_gap_s            = 1.5
require_viewer        = true
chat_exit_phrases     = ["end conversation", "that's all", "stop listening"]

[audit]
enabled = true
dir     = "audit"

[llm]
enabled                  = true
endpoint                 = "http://localhost:9931/v1/chat/completions"
temperature              = 0.7
max_tokens               = 1024
timeout_s                = 120.0
cache_prompt             = true
max_context_tokens       = 131072
compaction_safety_margin = 256
compaction_enabled       = true
compaction_trigger_ratio = 0.8
compaction_keep_turns    = 6
compaction_max_tokens    = 512
compaction_timeout_s     = 30.0
compaction_input_tokens  = 8192
compaction_system_prompt = "You compress a conversation. Preserve names, numbers, decisions, user preferences, and unresolved questions. Omit pleasantries. Output only the summary."
inference_queue_size     = 8
trim_block_turns         = 4
max_tool_iterations      = 3
system_prompt_chat       = "You are a concise voice assistant. Reply in 1-3 sentences."
system_prompt_command    = "You translate a spoken request into a single tool call when one applies."
triage_system_prompt     = "You extract structured signals from a spoken conversation. Output only a JSON object with exactly these keys: {\"summary\": str, \"opportunities\": [str], \"doubts\": [str], \"action_items\": [{\"what\": str, \"why\": str}], \"risks\": [str]}. Output no prose and no markdown fences. Use empty lists when a category is empty."

[triage]
enabled              = false
questions_file       = "questions.json"
window               = 500
state_char_budget    = 3000
predict_max_tokens   = 1024
confidence_field     = "answer_confidence"
escalate_threshold   = 0.6
choice_min_confidence = 0.85
extract_enabled      = true
extract_max_tokens   = 512
extract_timeout_s    = 30.0
device               = ""
preload              = ["multilingual"]
default_checkpoint   = "multilingual"