Botcompose FAQ's

    1. What are the built-in plugins available in BotCompose?

    STT Plugins

    • azure_fast

    • azure_real_time

    • deepgram

    • deepgram_streaming

    • google

    • google_streaming

    • sarvam

    LLM Plugins

    • openai_like 

    TTS Plugins

    • azure

    • cartesia

    • elevenlabs

    • google

    • openai

    • sarvam

    • smallestai

    2. Which STT plugins support streaming?

    Currently only these plugins support streaming STT in BotCompose:

    • deepgram_streaming

    • google_streaming


    3. How to enable streaming STT?

     Two requirements:

    • While adding bot set stt_config.plugin_name to: deepgram_streaming or google_streaming

    • In the make call payload set: "streaming_useraudio": true within the call_params.

    Both are required.

    4. Can plugin configurations be changed during a live call?

    Yes. BotCompose supports runtime plugin reconfiguration through built-in tools.

    For example:

    • Switch STT language dynamically

    • Change TTS voice/model mid-conversation

    A common use case is multilingual bots that detect language and switch STT/TTS configurations in real time.


    5. How does BotCompose handle observability and analytics?

    Every call generates a detailed CDR (Call Detail Record) JSON containing:

    • Call metadata

    • Full transcript

    • Tool invocation history

    • Latency metrics (STT / LLM / TTS)

    • Usage metrics (tokens, duration, cache savings)

    CDRs can be automatically pushed to partner systems for downstream processing.


    6. How does TTS caching work?

    BotCompose supports TTS caching to reduce latency and repeated provider calls.

    • Add reusable phrases while creating a bot 

    • When the LLM generates the same sentence, BotCompose serves audio from cache instead of requesting fresh synthesis from TTS.

    • This improves response speed and lowers TTS costs.


    7. How do I enable TTS cache?

    Define phrases inside:

    tts_cache_config.sentence_list

    Example:

    {

     "sentence": "Thank you for your valuable feedback and time.",

     "trim_silence": true

    }


    8. What is trim_silence?

    trim_silence removes leading and trailing silence from generated audio before storing it


    9. How do I get the call CDR?

    Pass a transcript_url in the call parameters.BotCompose will push the CDR as a JSON payload to that endpoint after the call completes. The CDR includes transcript, tool calls, timings, and call metadata.


    10. How do I access agent logs?

    Agent logs are available only in production environments.They are not exposed in sandbox setups.

    Published