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
session_dir     = "transcripts"
save_audio      = false
session_gap_min = 5.0

[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     = "troubleshoot/audit"

[llm]
enabled                        = true
endpoint                       = "http://localhost:9931/v1/chat/completions"
model                          = ""
api_key_env                    = ""
session_id                     = ""
session_header                 = ""
user_agent                     = ""
reasoning_effort               = ""
extra_body                     = {}
temperature                    = 0.7
max_tokens                     = 1024
timeout_s                      = 120.0
cache_prompt                   = true
chat_slot_id                   = ""
command_slot_id                = ""
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."
brief_compaction_system_prompt = "You compress a triage briefing conversation. Preserve every opportunity, blocker, owner, responsibility, decision, deadline, and open question; drop 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 maintain a living brief of a business conversation. The caller sends CURRENT LEDGER plus CURRENT BRIEF plus NEW UTTERANCES. Reply with exactly two sections in this order: NEW FACTS: first, then BRIEF:. Facts go first so a truncated reply still preserves extraction (truncation safety). In NEW FACTS:, emit one fact per line as '- <fact>', or the single line 'none' when the new utterances add no new facts. Never repeat facts already listed in CURRENT LEDGER. In BRIEF:, return the UPDATED brief as plain text only, with no markdown fences and no JSON. Open with a Summary section: a rolling overview of the conversation so far, one to a few sentences for a short session and growing to a short paragraph or two as the session extends. Preserve prior content unless the new utterances contradict it; merge duplicates; prune stale items; keep owners, responsibilities, and deadlines explicit. Use short sections: Summary, Opportunities, Blockers/Risks, Responsibilities, Decisions, Action Items, Deadlines, Open Questions. Never emit a 'Prior Details:' section. Output the two sections directly; never emit tool calls, function-call syntax, or special wrapper tokens."

[triage]
enabled                   = false
questions_file            = "questions.json"
window                    = 500
state_char_budget         = 3000
periodic_s                = 30.0
predict_max_tokens        = 1024
confidence_field          = "answer_confidence"
escalate_threshold        = 0.6
choice_min_confidence     = 0.85
extract_enabled           = true
extract_max_tokens        = 3072
extract_timeout_s         = 30.0
extract_temperature       = 0.2
brief_slot_id             = ""
brief_gate_enabled        = true
brief_gate_threshold      = 0.5
brief_max_chars           = 4000
brief_pending_char_budget = 3000
ledger_max_facts           = 200
fact_max_chars             = 240
device                    = ""
preload                   = ["multilingual"]
default_checkpoint        = "multilingual"
dump_io                   = false

[speaker]
enabled           = false
model_path        = ""
provider          = "cpu"
threshold_id      = 0.60
threshold_new     = 0.45
min_enroll_s      = 2.0
rms_floor         = 0.0
margin            = 0.04
mint_cooldown_s   = 60.0
confirm_s         = 12.0
max_prototypes    = 8
provisional_ttl_h = 24.0
store_dir         = "speakers"
join_timeout_s    = 2.0

[brief]
write = false

[debug]
enabled           = false
dir               = "troubleshoot/debug"
heartbeat         = true
max_bytes_per_day = 50000000