// Speak text aloud using the Magpie TTS container in the realtime-api Docker stack. Zero external dependencies — just curl + aplay.
| name | speak |
| description | Speak text aloud using the Magpie TTS container in the realtime-api Docker stack. Zero external dependencies — just curl + aplay. |
| triggers | ["speak","say","tell me","read aloud","announce"] |
Synthesize speech using the local Magpie TTS container (port 9000) and play through speakers.
/home/spark/git/autonomous-intelligence/realtime-api/scripts/speak.sh "Text to speak"
| Flag | Short | Default | Description |
|---|---|---|---|
| (positional) | (required) | Text to speak | |
--voice | -v | Mia.Calm | Voice name |
--speed | -s | 125 | Speed percentage |
--url | -u | http://localhost:9000 | Magpie TTS URL |
Mia, Mia.Calm, Mia.Happy, Mia.Sad, Mia.Angry, Aria, Aria.Calm, Aria.Happy, Jason, Jason.Calm, Leo, Leo.Calm
# Default calm voice
/home/spark/git/autonomous-intelligence/realtime-api/scripts/speak.sh "Deploy complete. All seven checks passed."
# Happy announcement
/home/spark/git/autonomous-intelligence/realtime-api/scripts/speak.sh -v Mia.Happy "All tests passed!"
# Different speed
/home/spark/git/autonomous-intelligence/realtime-api/scripts/speak.sh -s 140 "Speaking faster now."
Build and deploy the realtime-api Docker container with full verification that deployed code matches local source.
Run TTS round-trip tests — pure-logic unit tests and optional integration tests against live TTS/STT services.
Unified memory management for notes, knowledge graph, RAG search, and file analysis. Use when working with: (1) Core memory — protected identity, projects, relationships, and system facts that should never be forgotten, (2) Working notes — per-session ephemeral notes organized by section, (3) MongoDB RAG — vector-search-enabled notes with importance scoring, decay, deduplication, and archival, (4) Neo4j knowledge graph — entities, relationships, merge duplicates, reinforce mentions, Cypher queries, (5) File analysis — deep file reading that extracts knowledge into all memory layers, (6) Service initialization — health-check, start/stop MongoDB, Neo4j, TEI embeddings via docker-compose with partial setup support.
Query MongoDB notes store for memory analysis and statistics.
Query Neo4j knowledge graph for entities, relationships, and graph analysis.
Calls qq agent from cli.