Domains
Audio
Operations on the audio domain.
Audio Domain
The audio domain covers text-to-speech and audio analysis. Analysis returns text output because the modality is text.
Operations
| Operation | Output Modality | Namespace call |
|---|---|---|
speak | Audio | await celeste.audio.speak(...) |
analyze | Text | await celeste.audio.analyze(...) |
Examples
import celeste
from celeste.artifacts import AudioArtifact
# Speak → audio output
audio = await celeste.audio.speak(
model="eleven_multilingual_v2",
text="Hello from Celeste",
voice="Rachel",
)
# Analyze → text output
recording = AudioArtifact(path="recording.mp3")
summary = await celeste.audio.analyze(
model="gpt-4o",
prompt="Summarize this audio",
audio=recording,
)
print(summary.content)