Recommended settings

Use the settings below to get started with the API.

WebRTC settings

When publishing your audio track:

  • DTX: disabled
  • RED: disabled

Example with the LiveKit JS client:

await room.localParticipant.publishTrack(
    localTrack, { dtx: false, red: false, audioPreset: { maxBitrate: 32000, priority: "high" } }
);

Default pipeline settings

For a detailed description of each field and fine-tuning guidance, see the Translation settings breakdown or contact Palabra support.

{
  "input_stream": {
    "content_type": "audio",
    "source": {
      "type": "webrtc"
    }
  },
  "output_stream": {
    "content_type": "audio",
    "target": {
      "type": "webrtc"
    }
  },
  "pipeline": {
    "transcription": {
      "source_language": "en",
      "detectable_languages": [],
      "segment_confirmation_silence_threshold": 0.7,
      "sentence_splitter": {
        "enabled": true
      },
      "verification": {
        "auto_transcription_correction": false,
        "transcription_correction_style": null
      }
    },
    "translations": [
      {
        "target_language": "es",
        "translate_partial_transcriptions": false,
        "speech_generation": {
          "voice_cloning": false,
          "voice_id": "default_low",
          "voice_timbre_detection": {
            "enabled": false,
            "high_timbre_voices": [
              "default_high"
            ],
            "low_timbre_voices": [
              "default_low"
            ]
          }
        }
      }
    ],
    "translation_queue_configs": {
      "global": {
        "desired_queue_level_ms": 5000,
        "max_queue_level_ms": 20000,
        "auto_tempo": true,
        "min_tempo": 1.15,
        "max_tempo": 1.45
      }
    },
    "allowed_message_types": [
      "translated_transcription",
      "partial_transcription",
      "partial_translated_transcription",
      "validated_transcription"
    ]
  }
}