diff --git a/services/mana-stt/grafana-dashboard.json b/services/mana-stt/grafana-dashboard.json
new file mode 100644
index 000000000..398380ca7
--- /dev/null
+++ b/services/mana-stt/grafana-dashboard.json
@@ -0,0 +1,740 @@
+{
+	"annotations": {
+		"list": []
+	},
+	"description": "ManaCore Speech-to-Text Service Monitoring",
+	"editable": true,
+	"fiscalYearStartMonth": 0,
+	"graphTooltip": 1,
+	"links": [],
+	"panels": [
+		{
+			"collapsed": false,
+			"gridPos": { "h": 1, "w": 24, "x": 0, "y": 0 },
+			"id": 100,
+			"panels": [],
+			"title": "Overview",
+			"type": "row"
+		},
+		{
+			"datasource": { "type": "prometheus", "uid": "prometheus" },
+			"fieldConfig": {
+				"defaults": {
+					"color": { "mode": "thresholds" },
+					"mappings": [
+						{
+							"options": {
+								"0": { "color": "red", "index": 1, "text": "DOWN" },
+								"1": { "color": "green", "index": 0, "text": "UP" }
+							},
+							"type": "value"
+						}
+					],
+					"thresholds": {
+						"mode": "absolute",
+						"steps": [
+							{ "color": "red", "value": null },
+							{ "color": "green", "value": 1 }
+						]
+					}
+				},
+				"overrides": []
+			},
+			"gridPos": { "h": 4, "w": 3, "x": 0, "y": 1 },
+			"id": 1,
+			"options": {
+				"colorMode": "background",
+				"graphMode": "none",
+				"justifyMode": "auto",
+				"orientation": "auto",
+				"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
+				"textMode": "auto"
+			},
+			"pluginVersion": "10.4.1",
+			"targets": [
+				{
+					"datasource": { "type": "prometheus", "uid": "prometheus" },
+					"expr": "up{job=\"mana-stt\"}",
+					"refId": "A"
+				}
+			],
+			"title": "Service Status",
+			"type": "stat"
+		},
+		{
+			"datasource": { "type": "prometheus", "uid": "prometheus" },
+			"fieldConfig": {
+				"defaults": {
+					"color": { "mode": "thresholds" },
+					"mappings": [
+						{
+							"options": {
+								"0": { "color": "yellow", "index": 0, "text": "Not Loaded" },
+								"1": { "color": "green", "index": 1, "text": "Loaded" }
+							},
+							"type": "value"
+						}
+					],
+					"thresholds": {
+						"mode": "absolute",
+						"steps": [
+							{ "color": "yellow", "value": null },
+							{ "color": "green", "value": 1 }
+						]
+					}
+				},
+				"overrides": []
+			},
+			"gridPos": { "h": 4, "w": 3, "x": 3, "y": 1 },
+			"id": 2,
+			"options": {
+				"colorMode": "background",
+				"graphMode": "none",
+				"justifyMode": "auto",
+				"orientation": "auto",
+				"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
+				"textMode": "auto"
+			},
+			"targets": [
+				{
+					"datasource": { "type": "prometheus", "uid": "prometheus" },
+					"expr": "mana_stt_model_loaded{model=\"whisper\"}",
+					"refId": "A"
+				}
+			],
+			"title": "Whisper Model",
+			"type": "stat"
+		},
+		{
+			"datasource": { "type": "prometheus", "uid": "prometheus" },
+			"fieldConfig": {
+				"defaults": {
+					"color": { "mode": "thresholds" },
+					"mappings": [
+						{
+							"options": {
+								"0": { "color": "yellow", "index": 0, "text": "Not Loaded" },
+								"1": { "color": "green", "index": 1, "text": "Loaded" }
+							},
+							"type": "value"
+						}
+					],
+					"thresholds": {
+						"mode": "absolute",
+						"steps": [
+							{ "color": "yellow", "value": null },
+							{ "color": "green", "value": 1 }
+						]
+					}
+				},
+				"overrides": []
+			},
+			"gridPos": { "h": 4, "w": 3, "x": 6, "y": 1 },
+			"id": 3,
+			"options": {
+				"colorMode": "background",
+				"graphMode": "none",
+				"justifyMode": "auto",
+				"orientation": "auto",
+				"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
+				"textMode": "auto"
+			},
+			"targets": [
+				{
+					"datasource": { "type": "prometheus", "uid": "prometheus" },
+					"expr": "mana_stt_model_loaded{model=\"voxtral\"}",
+					"refId": "A"
+				}
+			],
+			"title": "Voxtral Model",
+			"type": "stat"
+		},
+		{
+			"datasource": { "type": "prometheus", "uid": "prometheus" },
+			"fieldConfig": {
+				"defaults": {
+					"color": { "mode": "palette-classic" },
+					"mappings": [],
+					"thresholds": { "mode": "absolute", "steps": [{ "color": "green", "value": null }] },
+					"unit": "short"
+				},
+				"overrides": []
+			},
+			"gridPos": { "h": 4, "w": 3, "x": 9, "y": 1 },
+			"id": 4,
+			"options": {
+				"colorMode": "value",
+				"graphMode": "area",
+				"justifyMode": "auto",
+				"orientation": "auto",
+				"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
+				"textMode": "auto"
+			},
+			"targets": [
+				{
+					"datasource": { "type": "prometheus", "uid": "prometheus" },
+					"expr": "sum(mana_stt_requests_total{status=\"success\"})",
+					"refId": "A"
+				}
+			],
+			"title": "Total Transcriptions",
+			"type": "stat"
+		},
+		{
+			"datasource": { "type": "prometheus", "uid": "prometheus" },
+			"fieldConfig": {
+				"defaults": {
+					"color": { "mode": "palette-classic" },
+					"mappings": [],
+					"thresholds": { "mode": "absolute", "steps": [{ "color": "green", "value": null }] },
+					"unit": "short"
+				},
+				"overrides": []
+			},
+			"gridPos": { "h": 4, "w": 3, "x": 12, "y": 1 },
+			"id": 5,
+			"options": {
+				"colorMode": "value",
+				"graphMode": "area",
+				"justifyMode": "auto",
+				"orientation": "auto",
+				"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
+				"textMode": "auto"
+			},
+			"targets": [
+				{
+					"datasource": { "type": "prometheus", "uid": "prometheus" },
+					"expr": "sum(mana_stt_characters_transcribed_total)",
+					"refId": "A"
+				}
+			],
+			"title": "Characters Transcribed",
+			"type": "stat"
+		},
+		{
+			"datasource": { "type": "prometheus", "uid": "prometheus" },
+			"fieldConfig": {
+				"defaults": {
+					"color": { "mode": "thresholds" },
+					"mappings": [],
+					"thresholds": {
+						"mode": "absolute",
+						"steps": [
+							{ "color": "green", "value": null },
+							{ "color": "yellow", "value": 1 },
+							{ "color": "red", "value": 3 }
+						]
+					},
+					"unit": "short"
+				},
+				"overrides": []
+			},
+			"gridPos": { "h": 4, "w": 3, "x": 15, "y": 1 },
+			"id": 6,
+			"options": {
+				"colorMode": "background",
+				"graphMode": "area",
+				"justifyMode": "auto",
+				"orientation": "auto",
+				"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
+				"textMode": "auto"
+			},
+			"targets": [
+				{
+					"datasource": { "type": "prometheus", "uid": "prometheus" },
+					"expr": "sum(mana_stt_active_requests)",
+					"refId": "A"
+				}
+			],
+			"title": "Active Requests",
+			"type": "stat"
+		},
+		{
+			"datasource": { "type": "prometheus", "uid": "prometheus" },
+			"fieldConfig": {
+				"defaults": {
+					"color": { "mode": "thresholds" },
+					"mappings": [],
+					"thresholds": {
+						"mode": "absolute",
+						"steps": [
+							{ "color": "green", "value": null },
+							{ "color": "red", "value": 1 }
+						]
+					},
+					"unit": "short"
+				},
+				"overrides": []
+			},
+			"gridPos": { "h": 4, "w": 3, "x": 18, "y": 1 },
+			"id": 7,
+			"options": {
+				"colorMode": "background",
+				"graphMode": "area",
+				"justifyMode": "auto",
+				"orientation": "auto",
+				"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
+				"textMode": "auto"
+			},
+			"targets": [
+				{
+					"datasource": { "type": "prometheus", "uid": "prometheus" },
+					"expr": "sum(mana_stt_requests_total{status=\"error\"})",
+					"refId": "A"
+				}
+			],
+			"title": "Total Errors",
+			"type": "stat"
+		},
+		{
+			"datasource": { "type": "prometheus", "uid": "prometheus" },
+			"fieldConfig": {
+				"defaults": {
+					"color": { "mode": "palette-classic" },
+					"mappings": [],
+					"thresholds": { "mode": "absolute", "steps": [{ "color": "green", "value": null }] },
+					"unit": "s"
+				},
+				"overrides": []
+			},
+			"gridPos": { "h": 4, "w": 3, "x": 21, "y": 1 },
+			"id": 8,
+			"options": {
+				"colorMode": "value",
+				"graphMode": "none",
+				"justifyMode": "auto",
+				"orientation": "auto",
+				"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
+				"textMode": "auto"
+			},
+			"targets": [
+				{
+					"datasource": { "type": "prometheus", "uid": "prometheus" },
+					"expr": "histogram_quantile(0.50, sum(rate(mana_stt_transcription_duration_seconds_bucket[5m])) by (le))",
+					"refId": "A"
+				}
+			],
+			"title": "Median Duration",
+			"type": "stat"
+		},
+		{
+			"collapsed": false,
+			"gridPos": { "h": 1, "w": 24, "x": 0, "y": 5 },
+			"id": 101,
+			"panels": [],
+			"title": "Performance",
+			"type": "row"
+		},
+		{
+			"datasource": { "type": "prometheus", "uid": "prometheus" },
+			"fieldConfig": {
+				"defaults": {
+					"color": { "mode": "palette-classic" },
+					"custom": {
+						"axisBorderShow": false,
+						"axisCenteredZero": false,
+						"axisColorMode": "text",
+						"axisLabel": "",
+						"axisPlacement": "auto",
+						"barAlignment": 0,
+						"drawStyle": "line",
+						"fillOpacity": 20,
+						"gradientMode": "none",
+						"hideFrom": { "legend": false, "tooltip": false, "viz": false },
+						"insertNulls": false,
+						"lineInterpolation": "smooth",
+						"lineWidth": 2,
+						"pointSize": 5,
+						"scaleDistribution": { "type": "linear" },
+						"showPoints": "auto",
+						"spanNulls": false,
+						"stacking": { "group": "A", "mode": "none" },
+						"thresholdsStyle": { "mode": "off" }
+					},
+					"mappings": [],
+					"thresholds": { "mode": "absolute", "steps": [{ "color": "green", "value": null }] },
+					"unit": "s"
+				},
+				"overrides": []
+			},
+			"gridPos": { "h": 8, "w": 12, "x": 0, "y": 6 },
+			"id": 10,
+			"options": {
+				"legend": {
+					"calcs": ["mean", "max"],
+					"displayMode": "table",
+					"placement": "bottom",
+					"showLegend": true
+				},
+				"tooltip": { "mode": "multi", "sort": "desc" }
+			},
+			"targets": [
+				{
+					"datasource": { "type": "prometheus", "uid": "prometheus" },
+					"expr": "histogram_quantile(0.50, sum(rate(mana_stt_transcription_duration_seconds_bucket{model=\"whisper\"}[5m])) by (le))",
+					"legendFormat": "Whisper p50",
+					"refId": "A"
+				},
+				{
+					"datasource": { "type": "prometheus", "uid": "prometheus" },
+					"expr": "histogram_quantile(0.95, sum(rate(mana_stt_transcription_duration_seconds_bucket{model=\"whisper\"}[5m])) by (le))",
+					"legendFormat": "Whisper p95",
+					"refId": "B"
+				},
+				{
+					"datasource": { "type": "prometheus", "uid": "prometheus" },
+					"expr": "histogram_quantile(0.50, sum(rate(mana_stt_transcription_duration_seconds_bucket{model=\"voxtral\"}[5m])) by (le))",
+					"legendFormat": "Voxtral p50",
+					"refId": "C"
+				},
+				{
+					"datasource": { "type": "prometheus", "uid": "prometheus" },
+					"expr": "histogram_quantile(0.95, sum(rate(mana_stt_transcription_duration_seconds_bucket{model=\"voxtral\"}[5m])) by (le))",
+					"legendFormat": "Voxtral p95",
+					"refId": "D"
+				}
+			],
+			"title": "Transcription Duration (p50 / p95)",
+			"type": "timeseries"
+		},
+		{
+			"datasource": { "type": "prometheus", "uid": "prometheus" },
+			"fieldConfig": {
+				"defaults": {
+					"color": { "mode": "palette-classic" },
+					"custom": {
+						"axisBorderShow": false,
+						"axisCenteredZero": false,
+						"axisColorMode": "text",
+						"axisLabel": "",
+						"axisPlacement": "auto",
+						"barAlignment": 0,
+						"drawStyle": "line",
+						"fillOpacity": 20,
+						"gradientMode": "none",
+						"hideFrom": { "legend": false, "tooltip": false, "viz": false },
+						"insertNulls": false,
+						"lineInterpolation": "smooth",
+						"lineWidth": 2,
+						"pointSize": 5,
+						"scaleDistribution": { "type": "linear" },
+						"showPoints": "auto",
+						"spanNulls": false,
+						"stacking": { "group": "A", "mode": "none" },
+						"thresholdsStyle": { "mode": "off" }
+					},
+					"mappings": [],
+					"thresholds": { "mode": "absolute", "steps": [{ "color": "green", "value": null }] },
+					"unit": "reqps"
+				},
+				"overrides": []
+			},
+			"gridPos": { "h": 8, "w": 12, "x": 12, "y": 6 },
+			"id": 11,
+			"options": {
+				"legend": {
+					"calcs": ["mean", "sum"],
+					"displayMode": "table",
+					"placement": "bottom",
+					"showLegend": true
+				},
+				"tooltip": { "mode": "multi", "sort": "desc" }
+			},
+			"targets": [
+				{
+					"datasource": { "type": "prometheus", "uid": "prometheus" },
+					"expr": "sum(rate(mana_stt_requests_total{model=\"whisper\", status=\"success\"}[5m]))",
+					"legendFormat": "Whisper Success",
+					"refId": "A"
+				},
+				{
+					"datasource": { "type": "prometheus", "uid": "prometheus" },
+					"expr": "sum(rate(mana_stt_requests_total{model=\"voxtral\", status=\"success\"}[5m]))",
+					"legendFormat": "Voxtral Success",
+					"refId": "B"
+				},
+				{
+					"datasource": { "type": "prometheus", "uid": "prometheus" },
+					"expr": "sum(rate(mana_stt_requests_total{status=\"error\"}[5m]))",
+					"legendFormat": "Errors",
+					"refId": "C"
+				}
+			],
+			"title": "Request Rate",
+			"type": "timeseries"
+		},
+		{
+			"collapsed": false,
+			"gridPos": { "h": 1, "w": 24, "x": 0, "y": 14 },
+			"id": 102,
+			"panels": [],
+			"title": "Details",
+			"type": "row"
+		},
+		{
+			"datasource": { "type": "prometheus", "uid": "prometheus" },
+			"fieldConfig": {
+				"defaults": {
+					"color": { "mode": "palette-classic" },
+					"custom": { "hideFrom": { "legend": false, "tooltip": false, "viz": false } },
+					"mappings": []
+				},
+				"overrides": []
+			},
+			"gridPos": { "h": 8, "w": 6, "x": 0, "y": 15 },
+			"id": 12,
+			"options": {
+				"legend": { "displayMode": "list", "placement": "right", "showLegend": true },
+				"pieType": "pie",
+				"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
+				"tooltip": { "mode": "single", "sort": "none" }
+			},
+			"targets": [
+				{
+					"datasource": { "type": "prometheus", "uid": "prometheus" },
+					"expr": "sum(mana_stt_requests_total{status=\"success\"}) by (model)",
+					"legendFormat": "{{model}}",
+					"refId": "A"
+				}
+			],
+			"title": "Requests by Model",
+			"type": "piechart"
+		},
+		{
+			"datasource": { "type": "prometheus", "uid": "prometheus" },
+			"fieldConfig": {
+				"defaults": {
+					"color": { "mode": "palette-classic" },
+					"custom": { "hideFrom": { "legend": false, "tooltip": false, "viz": false } },
+					"mappings": []
+				},
+				"overrides": []
+			},
+			"gridPos": { "h": 8, "w": 6, "x": 6, "y": 15 },
+			"id": 13,
+			"options": {
+				"legend": { "displayMode": "list", "placement": "right", "showLegend": true },
+				"pieType": "pie",
+				"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
+				"tooltip": { "mode": "single", "sort": "none" }
+			},
+			"targets": [
+				{
+					"datasource": { "type": "prometheus", "uid": "prometheus" },
+					"expr": "sum(mana_stt_requests_total{status=\"success\"}) by (language)",
+					"legendFormat": "{{language}}",
+					"refId": "A"
+				}
+			],
+			"title": "Requests by Language",
+			"type": "piechart"
+		},
+		{
+			"datasource": { "type": "prometheus", "uid": "prometheus" },
+			"fieldConfig": {
+				"defaults": {
+					"color": { "mode": "palette-classic" },
+					"custom": {
+						"axisBorderShow": false,
+						"axisCenteredZero": false,
+						"axisColorMode": "text",
+						"axisLabel": "",
+						"axisPlacement": "auto",
+						"barAlignment": 0,
+						"drawStyle": "bars",
+						"fillOpacity": 80,
+						"gradientMode": "none",
+						"hideFrom": { "legend": false, "tooltip": false, "viz": false },
+						"insertNulls": false,
+						"lineInterpolation": "linear",
+						"lineWidth": 1,
+						"pointSize": 5,
+						"scaleDistribution": { "type": "linear" },
+						"showPoints": "never",
+						"spanNulls": false,
+						"stacking": { "group": "A", "mode": "normal" },
+						"thresholdsStyle": { "mode": "off" }
+					},
+					"mappings": [],
+					"thresholds": { "mode": "absolute", "steps": [{ "color": "green", "value": null }] },
+					"unit": "decbytes"
+				},
+				"overrides": []
+			},
+			"gridPos": { "h": 8, "w": 12, "x": 12, "y": 15 },
+			"id": 14,
+			"options": {
+				"legend": { "calcs": [], "displayMode": "list", "placement": "bottom", "showLegend": true },
+				"tooltip": { "mode": "multi", "sort": "desc" }
+			},
+			"targets": [
+				{
+					"datasource": { "type": "prometheus", "uid": "prometheus" },
+					"expr": "sum(rate(mana_stt_file_size_mb_sum{model=\"whisper\"}[5m])) * 1024 * 1024",
+					"legendFormat": "Whisper",
+					"refId": "A"
+				},
+				{
+					"datasource": { "type": "prometheus", "uid": "prometheus" },
+					"expr": "sum(rate(mana_stt_file_size_mb_sum{model=\"voxtral\"}[5m])) * 1024 * 1024",
+					"legendFormat": "Voxtral",
+					"refId": "B"
+				}
+			],
+			"title": "Data Processed",
+			"type": "timeseries"
+		},
+		{
+			"collapsed": false,
+			"gridPos": { "h": 1, "w": 24, "x": 0, "y": 23 },
+			"id": 103,
+			"panels": [],
+			"title": "Model Loading",
+			"type": "row"
+		},
+		{
+			"datasource": { "type": "prometheus", "uid": "prometheus" },
+			"fieldConfig": {
+				"defaults": {
+					"color": { "mode": "thresholds" },
+					"mappings": [],
+					"thresholds": {
+						"mode": "absolute",
+						"steps": [
+							{ "color": "green", "value": null },
+							{ "color": "yellow", "value": 30 },
+							{ "color": "red", "value": 60 }
+						]
+					},
+					"unit": "s"
+				},
+				"overrides": []
+			},
+			"gridPos": { "h": 6, "w": 8, "x": 0, "y": 24 },
+			"id": 15,
+			"options": {
+				"colorMode": "value",
+				"graphMode": "area",
+				"justifyMode": "auto",
+				"orientation": "auto",
+				"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
+				"textMode": "auto"
+			},
+			"targets": [
+				{
+					"datasource": { "type": "prometheus", "uid": "prometheus" },
+					"expr": "mana_stt_model_load_duration_seconds_sum{model=\"whisper\"} / mana_stt_model_load_duration_seconds_count{model=\"whisper\"}",
+					"legendFormat": "Whisper",
+					"refId": "A"
+				}
+			],
+			"title": "Whisper Load Time",
+			"type": "stat"
+		},
+		{
+			"datasource": { "type": "prometheus", "uid": "prometheus" },
+			"fieldConfig": {
+				"defaults": {
+					"color": { "mode": "thresholds" },
+					"mappings": [],
+					"thresholds": {
+						"mode": "absolute",
+						"steps": [
+							{ "color": "green", "value": null },
+							{ "color": "yellow", "value": 60 },
+							{ "color": "red", "value": 120 }
+						]
+					},
+					"unit": "s"
+				},
+				"overrides": []
+			},
+			"gridPos": { "h": 6, "w": 8, "x": 8, "y": 24 },
+			"id": 16,
+			"options": {
+				"colorMode": "value",
+				"graphMode": "area",
+				"justifyMode": "auto",
+				"orientation": "auto",
+				"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
+				"textMode": "auto"
+			},
+			"targets": [
+				{
+					"datasource": { "type": "prometheus", "uid": "prometheus" },
+					"expr": "mana_stt_model_load_duration_seconds_sum{model=\"voxtral\"} / mana_stt_model_load_duration_seconds_count{model=\"voxtral\"}",
+					"legendFormat": "Voxtral",
+					"refId": "A"
+				}
+			],
+			"title": "Voxtral Load Time",
+			"type": "stat"
+		},
+		{
+			"datasource": { "type": "prometheus", "uid": "prometheus" },
+			"fieldConfig": {
+				"defaults": {
+					"color": { "mode": "palette-classic" },
+					"custom": {
+						"axisBorderShow": false,
+						"axisCenteredZero": false,
+						"axisColorMode": "text",
+						"axisLabel": "",
+						"axisPlacement": "auto",
+						"barAlignment": 0,
+						"drawStyle": "line",
+						"fillOpacity": 10,
+						"gradientMode": "none",
+						"hideFrom": { "legend": false, "tooltip": false, "viz": false },
+						"insertNulls": false,
+						"lineInterpolation": "smooth",
+						"lineWidth": 2,
+						"pointSize": 5,
+						"scaleDistribution": { "type": "linear" },
+						"showPoints": "auto",
+						"spanNulls": false,
+						"stacking": { "group": "A", "mode": "none" },
+						"thresholdsStyle": { "mode": "off" }
+					},
+					"mappings": [],
+					"thresholds": { "mode": "absolute", "steps": [{ "color": "green", "value": null }] },
+					"unit": "short"
+				},
+				"overrides": []
+			},
+			"gridPos": { "h": 6, "w": 8, "x": 16, "y": 24 },
+			"id": 17,
+			"options": {
+				"legend": { "calcs": [], "displayMode": "list", "placement": "bottom", "showLegend": true },
+				"tooltip": { "mode": "multi", "sort": "desc" }
+			},
+			"targets": [
+				{
+					"datasource": { "type": "prometheus", "uid": "prometheus" },
+					"expr": "sum(rate(mana_stt_characters_transcribed_total{model=\"whisper\"}[5m]))",
+					"legendFormat": "Whisper",
+					"refId": "A"
+				},
+				{
+					"datasource": { "type": "prometheus", "uid": "prometheus" },
+					"expr": "sum(rate(mana_stt_characters_transcribed_total{model=\"voxtral\"}[5m]))",
+					"legendFormat": "Voxtral",
+					"refId": "B"
+				}
+			],
+			"title": "Characters/sec Transcribed",
+			"type": "timeseries"
+		}
+	],
+	"refresh": "30s",
+	"schemaVersion": 39,
+	"tags": ["manacore", "stt", "ai"],
+	"templating": { "list": [] },
+	"time": { "from": "now-1h", "to": "now" },
+	"timepicker": {},
+	"timezone": "browser",
+	"title": "ManaCore STT Service",
+	"uid": "mana-stt-dashboard",
+	"version": 1,
+	"weekStart": "monday"
+}
diff --git a/services/ollama-metrics-proxy/grafana-dashboard.json b/services/ollama-metrics-proxy/grafana-dashboard.json
new file mode 100644
index 000000000..6fa5e171c
--- /dev/null
+++ b/services/ollama-metrics-proxy/grafana-dashboard.json
@@ -0,0 +1,595 @@
+{
+	"annotations": { "list": [] },
+	"description": "Ollama LLM Monitoring - Generation metrics, token usage, model performance",
+	"editable": true,
+	"fiscalYearStartMonth": 0,
+	"graphTooltip": 1,
+	"panels": [
+		{
+			"collapsed": false,
+			"gridPos": { "h": 1, "w": 24, "x": 0, "y": 0 },
+			"id": 100,
+			"panels": [],
+			"title": "Overview",
+			"type": "row"
+		},
+		{
+			"datasource": { "type": "prometheus", "uid": "${datasource}" },
+			"fieldConfig": {
+				"defaults": {
+					"color": { "mode": "thresholds" },
+					"mappings": [
+						{
+							"options": {
+								"0": { "color": "red", "text": "DOWN" },
+								"1": { "color": "green", "text": "UP" }
+							},
+							"type": "value"
+						}
+					],
+					"thresholds": {
+						"mode": "absolute",
+						"steps": [
+							{ "color": "red", "value": null },
+							{ "color": "green", "value": 1 }
+						]
+					}
+				}
+			},
+			"gridPos": { "h": 4, "w": 3, "x": 0, "y": 1 },
+			"id": 1,
+			"options": {
+				"colorMode": "background",
+				"graphMode": "none",
+				"justifyMode": "auto",
+				"orientation": "auto",
+				"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
+				"textMode": "auto"
+			},
+			"targets": [{ "expr": "up{job=\"ollama\"}", "refId": "A" }],
+			"title": "Proxy Status",
+			"type": "stat"
+		},
+		{
+			"datasource": { "type": "prometheus", "uid": "${datasource}" },
+			"fieldConfig": {
+				"defaults": {
+					"color": { "mode": "palette-classic" },
+					"mappings": [],
+					"thresholds": { "mode": "absolute", "steps": [{ "color": "green", "value": null }] },
+					"unit": "short"
+				}
+			},
+			"gridPos": { "h": 4, "w": 3, "x": 3, "y": 1 },
+			"id": 2,
+			"options": {
+				"colorMode": "value",
+				"graphMode": "area",
+				"justifyMode": "auto",
+				"orientation": "auto",
+				"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
+				"textMode": "auto"
+			},
+			"targets": [{ "expr": "sum(ollama_requests_total{status=\"success\"})", "refId": "A" }],
+			"title": "Total Requests",
+			"type": "stat"
+		},
+		{
+			"datasource": { "type": "prometheus", "uid": "${datasource}" },
+			"fieldConfig": {
+				"defaults": {
+					"color": { "mode": "palette-classic" },
+					"mappings": [],
+					"thresholds": { "mode": "absolute", "steps": [{ "color": "green", "value": null }] },
+					"unit": "short"
+				}
+			},
+			"gridPos": { "h": 4, "w": 3, "x": 6, "y": 1 },
+			"id": 3,
+			"options": {
+				"colorMode": "value",
+				"graphMode": "area",
+				"justifyMode": "auto",
+				"orientation": "auto",
+				"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
+				"textMode": "auto"
+			},
+			"targets": [{ "expr": "sum(ollama_tokens_generated_total)", "refId": "A" }],
+			"title": "Total Tokens Generated",
+			"type": "stat"
+		},
+		{
+			"datasource": { "type": "prometheus", "uid": "${datasource}" },
+			"fieldConfig": {
+				"defaults": {
+					"color": { "mode": "palette-classic" },
+					"mappings": [],
+					"thresholds": { "mode": "absolute", "steps": [{ "color": "green", "value": null }] },
+					"unit": "short"
+				}
+			},
+			"gridPos": { "h": 4, "w": 3, "x": 9, "y": 1 },
+			"id": 4,
+			"options": {
+				"colorMode": "value",
+				"graphMode": "area",
+				"justifyMode": "auto",
+				"orientation": "auto",
+				"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
+				"textMode": "auto"
+			},
+			"targets": [{ "expr": "sum(ollama_prompt_tokens_total)", "refId": "A" }],
+			"title": "Total Prompt Tokens",
+			"type": "stat"
+		},
+		{
+			"datasource": { "type": "prometheus", "uid": "${datasource}" },
+			"fieldConfig": {
+				"defaults": {
+					"color": { "mode": "thresholds" },
+					"mappings": [],
+					"thresholds": {
+						"mode": "absolute",
+						"steps": [
+							{ "color": "green", "value": null },
+							{ "color": "yellow", "value": 1 },
+							{ "color": "red", "value": 3 }
+						]
+					},
+					"unit": "short"
+				}
+			},
+			"gridPos": { "h": 4, "w": 3, "x": 12, "y": 1 },
+			"id": 5,
+			"options": {
+				"colorMode": "background",
+				"graphMode": "area",
+				"justifyMode": "auto",
+				"orientation": "auto",
+				"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
+				"textMode": "auto"
+			},
+			"targets": [{ "expr": "sum(ollama_active_requests)", "refId": "A" }],
+			"title": "Active Requests",
+			"type": "stat"
+		},
+		{
+			"datasource": { "type": "prometheus", "uid": "${datasource}" },
+			"fieldConfig": {
+				"defaults": {
+					"color": { "mode": "thresholds" },
+					"mappings": [],
+					"thresholds": {
+						"mode": "absolute",
+						"steps": [
+							{ "color": "green", "value": null },
+							{ "color": "red", "value": 1 }
+						]
+					},
+					"unit": "short"
+				}
+			},
+			"gridPos": { "h": 4, "w": 3, "x": 15, "y": 1 },
+			"id": 6,
+			"options": {
+				"colorMode": "background",
+				"graphMode": "area",
+				"justifyMode": "auto",
+				"orientation": "auto",
+				"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
+				"textMode": "auto"
+			},
+			"targets": [{ "expr": "sum(ollama_requests_total{status=\"error\"})", "refId": "A" }],
+			"title": "Total Errors",
+			"type": "stat"
+		},
+		{
+			"datasource": { "type": "prometheus", "uid": "${datasource}" },
+			"fieldConfig": {
+				"defaults": {
+					"color": { "mode": "palette-classic" },
+					"mappings": [],
+					"thresholds": { "mode": "absolute", "steps": [{ "color": "green", "value": null }] },
+					"unit": "s"
+				}
+			},
+			"gridPos": { "h": 4, "w": 3, "x": 18, "y": 1 },
+			"id": 7,
+			"options": {
+				"colorMode": "value",
+				"graphMode": "none",
+				"justifyMode": "auto",
+				"orientation": "auto",
+				"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
+				"textMode": "auto"
+			},
+			"targets": [
+				{
+					"expr": "histogram_quantile(0.50, sum(rate(ollama_generation_duration_seconds_bucket[5m])) by (le))",
+					"refId": "A"
+				}
+			],
+			"title": "Median Generation Time",
+			"type": "stat"
+		},
+		{
+			"datasource": { "type": "prometheus", "uid": "${datasource}" },
+			"fieldConfig": {
+				"defaults": {
+					"color": { "mode": "palette-classic" },
+					"mappings": [],
+					"thresholds": { "mode": "absolute", "steps": [{ "color": "green", "value": null }] },
+					"unit": "s"
+				}
+			},
+			"gridPos": { "h": 4, "w": 3, "x": 21, "y": 1 },
+			"id": 8,
+			"options": {
+				"colorMode": "value",
+				"graphMode": "none",
+				"justifyMode": "auto",
+				"orientation": "auto",
+				"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
+				"textMode": "auto"
+			},
+			"targets": [
+				{
+					"expr": "histogram_quantile(0.50, sum(rate(ollama_time_to_first_token_seconds_bucket[5m])) by (le))",
+					"refId": "A"
+				}
+			],
+			"title": "Median TTFT",
+			"type": "stat"
+		},
+		{
+			"collapsed": false,
+			"gridPos": { "h": 1, "w": 24, "x": 0, "y": 5 },
+			"id": 101,
+			"panels": [],
+			"title": "Performance",
+			"type": "row"
+		},
+		{
+			"datasource": { "type": "prometheus", "uid": "${datasource}" },
+			"fieldConfig": {
+				"defaults": {
+					"color": { "mode": "palette-classic" },
+					"custom": {
+						"axisBorderShow": false,
+						"axisCenteredZero": false,
+						"axisColorMode": "text",
+						"axisLabel": "",
+						"axisPlacement": "auto",
+						"barAlignment": 0,
+						"drawStyle": "line",
+						"fillOpacity": 20,
+						"gradientMode": "none",
+						"hideFrom": { "legend": false, "tooltip": false, "viz": false },
+						"insertNulls": false,
+						"lineInterpolation": "smooth",
+						"lineWidth": 2,
+						"pointSize": 5,
+						"scaleDistribution": { "type": "linear" },
+						"showPoints": "auto",
+						"spanNulls": false,
+						"stacking": { "group": "A", "mode": "none" },
+						"thresholdsStyle": { "mode": "off" }
+					},
+					"mappings": [],
+					"thresholds": { "mode": "absolute", "steps": [{ "color": "green", "value": null }] },
+					"unit": "s"
+				}
+			},
+			"gridPos": { "h": 8, "w": 12, "x": 0, "y": 6 },
+			"id": 10,
+			"options": {
+				"legend": {
+					"calcs": ["mean", "max"],
+					"displayMode": "table",
+					"placement": "bottom",
+					"showLegend": true
+				},
+				"tooltip": { "mode": "multi", "sort": "desc" }
+			},
+			"targets": [
+				{
+					"expr": "histogram_quantile(0.50, sum(rate(ollama_generation_duration_seconds_bucket[5m])) by (le, model))",
+					"legendFormat": "{{model}} p50",
+					"refId": "A"
+				},
+				{
+					"expr": "histogram_quantile(0.95, sum(rate(ollama_generation_duration_seconds_bucket[5m])) by (le, model))",
+					"legendFormat": "{{model}} p95",
+					"refId": "B"
+				}
+			],
+			"title": "Generation Duration by Model (p50 / p95)",
+			"type": "timeseries"
+		},
+		{
+			"datasource": { "type": "prometheus", "uid": "${datasource}" },
+			"fieldConfig": {
+				"defaults": {
+					"color": { "mode": "palette-classic" },
+					"custom": {
+						"axisBorderShow": false,
+						"axisCenteredZero": false,
+						"axisColorMode": "text",
+						"axisLabel": "",
+						"axisPlacement": "auto",
+						"barAlignment": 0,
+						"drawStyle": "line",
+						"fillOpacity": 20,
+						"gradientMode": "none",
+						"hideFrom": { "legend": false, "tooltip": false, "viz": false },
+						"insertNulls": false,
+						"lineInterpolation": "smooth",
+						"lineWidth": 2,
+						"pointSize": 5,
+						"scaleDistribution": { "type": "linear" },
+						"showPoints": "auto",
+						"spanNulls": false,
+						"stacking": { "group": "A", "mode": "none" },
+						"thresholdsStyle": { "mode": "off" }
+					},
+					"mappings": [],
+					"thresholds": { "mode": "absolute", "steps": [{ "color": "green", "value": null }] },
+					"unit": "s"
+				}
+			},
+			"gridPos": { "h": 8, "w": 12, "x": 12, "y": 6 },
+			"id": 11,
+			"options": {
+				"legend": {
+					"calcs": ["mean", "max"],
+					"displayMode": "table",
+					"placement": "bottom",
+					"showLegend": true
+				},
+				"tooltip": { "mode": "multi", "sort": "desc" }
+			},
+			"targets": [
+				{
+					"expr": "histogram_quantile(0.50, sum(rate(ollama_time_to_first_token_seconds_bucket[5m])) by (le, model))",
+					"legendFormat": "{{model}} p50",
+					"refId": "A"
+				},
+				{
+					"expr": "histogram_quantile(0.95, sum(rate(ollama_time_to_first_token_seconds_bucket[5m])) by (le, model))",
+					"legendFormat": "{{model}} p95",
+					"refId": "B"
+				}
+			],
+			"title": "Time to First Token by Model (p50 / p95)",
+			"type": "timeseries"
+		},
+		{
+			"collapsed": false,
+			"gridPos": { "h": 1, "w": 24, "x": 0, "y": 14 },
+			"id": 102,
+			"panels": [],
+			"title": "Token Usage",
+			"type": "row"
+		},
+		{
+			"datasource": { "type": "prometheus", "uid": "${datasource}" },
+			"fieldConfig": {
+				"defaults": {
+					"color": { "mode": "palette-classic" },
+					"custom": {
+						"axisBorderShow": false,
+						"axisCenteredZero": false,
+						"axisColorMode": "text",
+						"axisLabel": "",
+						"axisPlacement": "auto",
+						"barAlignment": 0,
+						"drawStyle": "line",
+						"fillOpacity": 30,
+						"gradientMode": "none",
+						"hideFrom": { "legend": false, "tooltip": false, "viz": false },
+						"insertNulls": false,
+						"lineInterpolation": "smooth",
+						"lineWidth": 2,
+						"pointSize": 5,
+						"scaleDistribution": { "type": "linear" },
+						"showPoints": "auto",
+						"spanNulls": false,
+						"stacking": { "group": "A", "mode": "normal" },
+						"thresholdsStyle": { "mode": "off" }
+					},
+					"mappings": [],
+					"thresholds": { "mode": "absolute", "steps": [{ "color": "green", "value": null }] },
+					"unit": "short"
+				}
+			},
+			"gridPos": { "h": 8, "w": 12, "x": 0, "y": 15 },
+			"id": 12,
+			"options": {
+				"legend": {
+					"calcs": ["sum"],
+					"displayMode": "table",
+					"placement": "bottom",
+					"showLegend": true
+				},
+				"tooltip": { "mode": "multi", "sort": "desc" }
+			},
+			"targets": [
+				{
+					"expr": "sum(rate(ollama_tokens_generated_total[5m])) by (model)",
+					"legendFormat": "{{model}}",
+					"refId": "A"
+				}
+			],
+			"title": "Tokens Generated per Second by Model",
+			"type": "timeseries"
+		},
+		{
+			"datasource": { "type": "prometheus", "uid": "${datasource}" },
+			"fieldConfig": {
+				"defaults": {
+					"color": { "mode": "palette-classic" },
+					"custom": {
+						"axisBorderShow": false,
+						"axisCenteredZero": false,
+						"axisColorMode": "text",
+						"axisLabel": "",
+						"axisPlacement": "auto",
+						"barAlignment": 0,
+						"drawStyle": "line",
+						"fillOpacity": 30,
+						"gradientMode": "none",
+						"hideFrom": { "legend": false, "tooltip": false, "viz": false },
+						"insertNulls": false,
+						"lineInterpolation": "smooth",
+						"lineWidth": 2,
+						"pointSize": 5,
+						"scaleDistribution": { "type": "linear" },
+						"showPoints": "auto",
+						"spanNulls": false,
+						"stacking": { "group": "A", "mode": "normal" },
+						"thresholdsStyle": { "mode": "off" }
+					},
+					"mappings": [],
+					"thresholds": { "mode": "absolute", "steps": [{ "color": "green", "value": null }] },
+					"unit": "reqps"
+				}
+			},
+			"gridPos": { "h": 8, "w": 12, "x": 12, "y": 15 },
+			"id": 13,
+			"options": {
+				"legend": {
+					"calcs": ["mean", "sum"],
+					"displayMode": "table",
+					"placement": "bottom",
+					"showLegend": true
+				},
+				"tooltip": { "mode": "multi", "sort": "desc" }
+			},
+			"targets": [
+				{
+					"expr": "sum(rate(ollama_requests_total{status=\"success\"}[5m])) by (model)",
+					"legendFormat": "{{model}}",
+					"refId": "A"
+				}
+			],
+			"title": "Requests per Second by Model",
+			"type": "timeseries"
+		},
+		{
+			"collapsed": false,
+			"gridPos": { "h": 1, "w": 24, "x": 0, "y": 23 },
+			"id": 103,
+			"panels": [],
+			"title": "Model Distribution",
+			"type": "row"
+		},
+		{
+			"datasource": { "type": "prometheus", "uid": "${datasource}" },
+			"fieldConfig": {
+				"defaults": {
+					"color": { "mode": "palette-classic" },
+					"custom": { "hideFrom": { "legend": false, "tooltip": false, "viz": false } },
+					"mappings": []
+				}
+			},
+			"gridPos": { "h": 8, "w": 8, "x": 0, "y": 24 },
+			"id": 14,
+			"options": {
+				"legend": { "displayMode": "list", "placement": "right", "showLegend": true },
+				"pieType": "pie",
+				"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
+				"tooltip": { "mode": "single", "sort": "none" }
+			},
+			"targets": [
+				{
+					"expr": "sum(ollama_requests_total{status=\"success\"}) by (model)",
+					"legendFormat": "{{model}}",
+					"refId": "A"
+				}
+			],
+			"title": "Requests by Model",
+			"type": "piechart"
+		},
+		{
+			"datasource": { "type": "prometheus", "uid": "${datasource}" },
+			"fieldConfig": {
+				"defaults": {
+					"color": { "mode": "palette-classic" },
+					"custom": { "hideFrom": { "legend": false, "tooltip": false, "viz": false } },
+					"mappings": []
+				}
+			},
+			"gridPos": { "h": 8, "w": 8, "x": 8, "y": 24 },
+			"id": 15,
+			"options": {
+				"legend": { "displayMode": "list", "placement": "right", "showLegend": true },
+				"pieType": "pie",
+				"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
+				"tooltip": { "mode": "single", "sort": "none" }
+			},
+			"targets": [
+				{
+					"expr": "sum(ollama_tokens_generated_total) by (model)",
+					"legendFormat": "{{model}}",
+					"refId": "A"
+				}
+			],
+			"title": "Tokens by Model",
+			"type": "piechart"
+		},
+		{
+			"datasource": { "type": "prometheus", "uid": "${datasource}" },
+			"fieldConfig": {
+				"defaults": {
+					"color": { "mode": "palette-classic" },
+					"custom": { "hideFrom": { "legend": false, "tooltip": false, "viz": false } },
+					"mappings": []
+				}
+			},
+			"gridPos": { "h": 8, "w": 8, "x": 16, "y": 24 },
+			"id": 16,
+			"options": {
+				"legend": { "displayMode": "list", "placement": "right", "showLegend": true },
+				"pieType": "pie",
+				"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
+				"tooltip": { "mode": "single", "sort": "none" }
+			},
+			"targets": [
+				{
+					"expr": "sum(ollama_requests_total{status=\"success\"}) by (endpoint)",
+					"legendFormat": "{{endpoint}}",
+					"refId": "A"
+				}
+			],
+			"title": "Requests by Endpoint",
+			"type": "piechart"
+		}
+	],
+	"refresh": "30s",
+	"schemaVersion": 39,
+	"tags": ["manacore", "ollama", "llm", "ai"],
+	"templating": {
+		"list": [
+			{
+				"current": { "selected": false, "text": "Prometheus", "value": "Prometheus" },
+				"hide": 0,
+				"includeAll": false,
+				"multi": false,
+				"name": "datasource",
+				"options": [],
+				"query": "prometheus",
+				"refresh": 1,
+				"regex": "",
+				"skipUrlSync": false,
+				"type": "datasource"
+			}
+		]
+	},
+	"time": { "from": "now-1h", "to": "now" },
+	"timepicker": {},
+	"timezone": "browser",
+	"title": "Ollama LLM Service",
+	"uid": "ollama-dashboard",
+	"version": 1,
+	"weekStart": "monday"
+}
diff --git a/services/telegram-project-doc-bot/.env.example b/services/telegram-project-doc-bot/.env.example
index 6a57b14a2..ecc6c0fc0 100644
--- a/services/telegram-project-doc-bot/.env.example
+++ b/services/telegram-project-doc-bot/.env.example
@@ -15,10 +15,15 @@ S3_ACCESS_KEY=minioadmin
 S3_SECRET_KEY=minioadmin
 S3_BUCKET=projectdoc-storage
 
-# AI - Transcription (OpenAI Whisper)
+# AI - Transcription (STT)
+STT_PROVIDER=local              # local | openai
+STT_LOCAL_URL=http://localhost:3020  # mana-stt service URL
+STT_MODEL=whisper               # whisper | voxtral
+
+# OpenAI (optional fallback for STT, required if STT_PROVIDER=openai)
 OPENAI_API_KEY=sk-your-openai-key
 
 # AI - Generation
 LLM_PROVIDER=ollama  # ollama | openai
-OLLAMA_URL=http://localhost:11434
+OLLAMA_URL=http://localhost:11435  # Use :11435 for metrics proxy, :11434 for direct
 OLLAMA_MODEL=gemma3:4b
diff --git a/services/telegram-project-doc-bot/src/config/configuration.ts b/services/telegram-project-doc-bot/src/config/configuration.ts
index 2ee99c866..467903802 100644
--- a/services/telegram-project-doc-bot/src/config/configuration.ts
+++ b/services/telegram-project-doc-bot/src/config/configuration.ts
@@ -20,6 +20,11 @@ export default () => ({
 	openai: {
 		apiKey: process.env.OPENAI_API_KEY,
 	},
+	stt: {
+		provider: process.env.STT_PROVIDER || 'local', // 'local' or 'openai'
+		localUrl: process.env.STT_LOCAL_URL || 'http://localhost:3020',
+		model: process.env.STT_MODEL || 'whisper', // 'whisper' or 'voxtral'
+	},
 	llm: {
 		provider: process.env.LLM_PROVIDER || 'ollama',
 		ollama: {
diff --git a/services/telegram-project-doc-bot/src/database/schema.ts b/services/telegram-project-doc-bot/src/database/schema.ts
index 10c2fb2db..371bc9c20 100644
--- a/services/telegram-project-doc-bot/src/database/schema.ts
+++ b/services/telegram-project-doc-bot/src/database/schema.ts
@@ -1,10 +1,19 @@
-import { pgTable, uuid, text, timestamp, integer, jsonb, boolean } from 'drizzle-orm/pg-core';
+import {
+	pgTable,
+	uuid,
+	text,
+	timestamp,
+	integer,
+	bigint,
+	jsonb,
+	boolean,
+} from 'drizzle-orm/pg-core';
 import { relations } from 'drizzle-orm';
 
 // Projects table
 export const projects = pgTable('projects', {
 	id: uuid('id').primaryKey().defaultRandom(),
-	telegramUserId: integer('telegram_user_id').notNull(),
+	telegramUserId: bigint('telegram_user_id', { mode: 'number' }).notNull(),
 	name: text('name').notNull(),
 	description: text('description'),
 	status: text('status').default('active').notNull(), // active, archived, completed
diff --git a/services/telegram-project-doc-bot/src/transcription/transcription.service.ts b/services/telegram-project-doc-bot/src/transcription/transcription.service.ts
index 631a7b84a..74d7f5af9 100644
--- a/services/telegram-project-doc-bot/src/transcription/transcription.service.ts
+++ b/services/telegram-project-doc-bot/src/transcription/transcription.service.ts
@@ -2,48 +2,115 @@ import { Injectable, Logger } from '@nestjs/common';
 import { ConfigService } from '@nestjs/config';
 import OpenAI from 'openai';
 
+interface LocalSTTResponse {
+	text: string;
+	language?: string;
+	model: string;
+}
+
 @Injectable()
 export class TranscriptionService {
 	private readonly logger = new Logger(TranscriptionService.name);
 	private readonly openai: OpenAI | null;
+	private readonly provider: 'local' | 'openai';
+	private readonly localUrl: string;
+	private readonly sttModel: string;
 
 	constructor(private configService: ConfigService) {
+		this.provider = this.configService.get<string>('stt.provider', 'local') as 'local' | 'openai';
+		this.localUrl = this.configService.get<string>('stt.localUrl', 'http://localhost:3020');
+		this.sttModel = this.configService.get<string>('stt.model', 'whisper');
+
 		const apiKey = this.configService.get<string>('openai.apiKey');
 
 		if (apiKey) {
 			this.openai = new OpenAI({ apiKey });
-			this.logger.log('OpenAI Whisper initialized');
+			this.logger.log('OpenAI Whisper available as fallback');
 		} else {
 			this.openai = null;
-			this.logger.warn('OpenAI API key not configured - transcription disabled');
 		}
+
+		this.logger.log(
+			`STT Provider: ${this.provider}, URL: ${this.localUrl}, Model: ${this.sttModel}`
+		);
 	}
 
 	async transcribe(audioBuffer: Buffer, filename = 'audio.ogg'): Promise<string> {
+		// Try local STT first if configured
+		if (this.provider === 'local') {
+			try {
+				return await this.transcribeLocal(audioBuffer, filename);
+			} catch (error) {
+				this.logger.warn(`Local STT failed, trying OpenAI fallback: ${error}`);
+				if (this.openai) {
+					return await this.transcribeOpenAI(audioBuffer, filename);
+				}
+				throw error;
+			}
+		}
+
+		// Use OpenAI
+		if (this.openai) {
+			return await this.transcribeOpenAI(audioBuffer, filename);
+		}
+
+		throw new Error('No STT provider available');
+	}
+
+	private async transcribeLocal(audioBuffer: Buffer, filename: string): Promise<string> {
+		const endpoint = this.sttModel === 'voxtral' ? '/transcribe/voxtral' : '/transcribe';
+		const url = `${this.localUrl}${endpoint}`;
+
+		this.logger.debug(`Calling local STT: ${url}`);
+
+		const formData = new FormData();
+		const uint8Array = new Uint8Array(audioBuffer);
+		const blob = new Blob([uint8Array], { type: 'audio/ogg' });
+		formData.append('file', blob, filename);
+		formData.append('language', 'de');
+
+		const response = await fetch(url, {
+			method: 'POST',
+			body: formData,
+		});
+
+		if (!response.ok) {
+			const error = await response.text();
+			throw new Error(`Local STT error: ${response.status} - ${error}`);
+		}
+
+		const result: LocalSTTResponse = await response.json();
+		this.logger.debug(`Local STT result: ${result.text.length} chars, model: ${result.model}`);
+
+		return result.text;
+	}
+
+	private async transcribeOpenAI(audioBuffer: Buffer, filename: string): Promise<string> {
 		if (!this.openai) {
-			throw new Error('Transcription not available - OpenAI API key not configured');
+			throw new Error('OpenAI not configured');
 		}
 
 		try {
-			// Create a File object from the buffer using Uint8Array
 			const uint8Array = new Uint8Array(audioBuffer);
 			const file = new File([uint8Array], filename, { type: 'audio/ogg' });
 
 			const response = await this.openai.audio.transcriptions.create({
 				file,
 				model: 'whisper-1',
-				language: 'de', // Default to German, could be made configurable
+				language: 'de',
 			});
 
-			this.logger.debug(`Transcribed ${audioBuffer.length} bytes -> ${response.text.length} chars`);
+			this.logger.debug(
+				`OpenAI transcribed ${audioBuffer.length} bytes -> ${response.text.length} chars`
+			);
 			return response.text;
 		} catch (error) {
-			this.logger.error('Transcription failed:', error);
+			this.logger.error('OpenAI transcription failed:', error);
 			throw new Error('Transkription fehlgeschlagen');
 		}
 	}
 
 	isAvailable(): boolean {
-		return this.openai !== null;
+		return this.provider === 'local' || this.openai !== null;
 	}
 }