Skip to main content
The PolyAI platform supports flexible voice selection for external providers such as ElevenLabs, AWS Polly, and Microsoft Azure TTS.

​
Provider classes

When picking models, adjusting stability, or accessing third-party providers — use provider-specific TTSVoice classes. You can also optionally adjust clarity and latency_mode to match the agent’s interaction style.

​
Example: ElevenLabs

from polyai.voice import ElevenLabsVoice

conv.set_voice(
    ElevenLabsVoice(
        provider_voice_id="gDnGxUcsitTxRiGHr904",
        model_id="eleven_flash_v2",
        stability=0.5,
        similarity_boost=0.7,
        clarity=0.8,            # Optional: controls crispness of enunciation
        latency_mode="swift",   # Optional: aligns with interaction-style settings
    )
)

​
Example: AWS Polly

from polyai.voice import PollyVoice 
conv.set_voice(
    PollyVoice(
        provider_voice_id="Joanna",
        engine="neural",
        clarity=0.6,
    )
)

​
Example: Microsoft Azure TTS

from polyai.voice import AzureVoice

conv.set_voice(
    AzureVoice(
        provider_voice_id="en-US-JennyNeural",
        style="cheerful",
        role="customer-service-rep",
        clarity=0.9,
    )
)

​
Cache behavior

  • Changing model_id does not automatically invalidate cached audio.
  • To reset cached audio:
    • Go to Audio → Cache and delete existing entries.
    • Or, create a new voice entry with a different voice_id.
    • You can prepend the model ID to the voice ID (e.g. eleven_flash_v2/a1b2c3...) if you want to isolate caches across models.

​
Additional options

  • clarity – fine-tunes articulation sharpness per utterance (0.0–1.0).
  • latency_mode – chooses a response profile (“swift”, “balanced”, “precise”, “turbo”) consistent with Interaction style.
  • stability – controls tone variability across runs.
  • randomize_voice() – supports external providers for weighted selection.