First-party
Below is the complete skill definition this hub loads when the skill is triggered — what the agent sees as its instructions, verbatim and unabridged.
# AXE Speech
Speech-to-text and text-to-speech on fleet hardware.
## ASR (Newton Speech / Parakeet)
Parakeet GGUF model running on fleet nodes via `newton_speech.sh`.
```bash
ssh forge "cd ~/Desktop/newton/speech && bash newton_speech.sh /tmp/audio.wav"
```
Or via Siren API:
```bash
curl -s -X POST https://siren.onl/api/transcribe \
-H "X-AXE-Key: $AXE_FLEET_KEY" \
-F "[email protected]"
```
## TTS (Siren)
```bash
curl -s -X POST https://siren.onl/api/speak \
-H "X-AXE-Key: $AXE_FLEET_KEY" \
-H "Content-Type: application/json" \
-d '{"text":"<utterance>","voice":"ghost"}' \
--output speech.wav
```
## Fleet Nodes
| Node | Capability | Status |
|------|-----------|--------|
| Forge (JL2) | Parakeet ASR | Active |
| AXeServer | Siren TTS+ASR | Active |
## Python
```python
import subprocess
def transcribe(audio_path, node="forge"):
result = subprocess.run(["ssh", node, f"cd ~/Desktop/newton/speech && bash newton_speech.sh {audio_path}"], capture_output=True, text=True)
return result.stdout.strip()
```Speech-to-text and text-to-speech on fleet hardware.
Parakeet GGUF model running on fleet nodes via newton_speech.sh.
ssh forge "cd ~/Desktop/newton/speech && bash newton_speech.sh /tmp/audio.wav"
Or via Siren API:
curl -s -X POST https://siren.onl/api/transcribe \
-H "X-AXE-Key: $AXE_FLEET_KEY" \
-F "[email protected]"
curl -s -X POST https://siren.onl/api/speak \
-H "X-AXE-Key: $AXE_FLEET_KEY" \
-H "Content-Type: application/json" \
-d '{"text":"<utterance>","voice":"ghost"}' \
--output speech.wav
| Node | Capability | Status |
|---|---|---|
| Forge (JL2) | Parakeet ASR | Active |
| AXeServer | Siren TTS+ASR | Active |
import subprocess
def transcribe(audio_path, node="forge"):
result = subprocess.run(["ssh", node, f"cd ~/Desktop/newton/speech && bash newton_speech.sh {audio_path}"], capture_output=True, text=True)
return result.stdout.strip()
Fetch this skill’s definition over the open API — no key required.
curl -s /v1/skills/axe-speech