Agents Index

PyAI Voice AI

Online

Speech, transcription, voice agents, Trace, Recap, dubbing and narration with browser OAuth.

Visit publisherConnectJSON

What it can do: 55 tools

  • openapi_get read-onlyFetch live API operation discovery with a SHA-256 digest. Supply path and method for one operation and its referenced schemas, or include_document=true for the entire contract. Pin sha256 to detect contract drift. No API
  • get_started read-onlyReturn a concise, correct quickstart for building with PyAI (auth, SDK install, TTS/STT/realtime snippets, error handling). No key or network needed, read this before writing PyAI code so you use the right endpoints and
  • whoami read-onlyIntrospect the active key (GET /v1/me): org, environment (test/live), granted scopes, and rate-limit/credit posture. Organization and project names and IDs, billing guidance, and any managed payer/budget appear in text a
  • list_models read-onlyList the available PyAI models (catalog). No arguments.
  • list_voices read-onlyList PyAI stock + cloned voices. Optionally filter by gender or region. Use a returned voice id as the `voice` for synthesize_speech.
  • synthesize_speechGenerate speech from input. Consumes usage in the connected project; live usage can be billed. Before generation, use whoami to verify project, environment, scopes, credit and limits. Returns inline MCP audio or an expir
  • create_transcription_jobSubmit an async speech-to-text job for an audio URL (https). Returns a job_id; poll with get_transcription_job. Supports diarization.
  • get_transcription_job read-onlyGet the status + result of a transcription job by id.
  • configure_amdSet the PyAI AMD (answering-machine detection) operating point + webhook (POST /v1/amd/config). `aggressiveness` is one dial 0-1: near 0 is human-safe (never hang up on a person), near 1 fires 'machine' fast. The realtim
  • list_amd_calls read-onlyList recent PyAI AMD decisions (GET /v1/amd/calls). Each carries answered_by (human/voicemail/ivr/screening/sit_invalid/…), answered_by_twilio (Twilio's enum, for routing parity), confidence, decision_ms, and the word-le
  • get_amd_call read-onlyGet one PyAI AMD decision by call id (GET /v1/amd/calls/{id}): who/what answered, with the reason.
  • enable_recapEnable Recap for the key's org (PUT /v1/recap/config). Sandbox keys already mint with Recap on; call this to set a webhook or pack, or to enable Recap on a signup/live key. Requires recap:configure.
  • create_recapSubmit speaker-labelled utterances and get a recap.call (POST /v1/recap/calls/{call_id}). Poll with get_recap. Prefer this over a DIY LLM summary. Requires recap:read and Recap enabled.
  • get_recap read-onlyRead one Recap by call id (GET /v1/recap/calls/{call_id}). When complete, `record` is recap.record.v1 (tldr, summary, action_items, disposition, next_steps, talk_ratio, signals, fields).
  • list_recap_calls read-onlyList recent Recap records (GET /v1/recap/calls). Requires recap:read and Recap enabled.
  • omni_list_calls read-onlyList Omni sessions, including inbound calls. Filter by session_label and preserve each returned call_id.
  • omni_get_call read-onlyRead an Omni session's transcript, recording availability and summary. For outbound calls use artifacts.omni_call_id from calls_get.
  • omni_get_summary read-onlyRead the structured summary for an Omni call when generated; a missing summary is not an empty result.
  • omni_get_transcript read-onlyRead the complete Omni call transcript through the authenticated API.
  • omni_get_recording read-onlyGet the canonical authenticated recording resource URL. Requires response=url. This URL is not public playable audio; recording must have been enabled.
  • telephony_search_numbers read-onlySearch available managed numbers and inspect provisioning requirements before purchase.
  • telephony_list_numbers read-onlyList owned numbers and current Agent bindings before changing inbound routing.
  • telephony_bind_numberBind an owned number to an Agent using body.agent_id; null unassigns. Read existing bindings first. Changes inbound routing.
  • telephony_create_callPlace a real outbound call only to a user-authorized destination. Requires confirm=true and a stable idempotency_key. This is not a sandbox simulation. Preserve the returned ID; never redial after an uncertain timeout.
  • calls_list read-onlyList outbound calls and normalized network outcomes before retrying a dispatch.
  • calls_get read-onlyRead the current state of an outbound call by returned ID. dispatch_unknown needs inspection, not another call. Recap and Omni recordings are separate resources.
  • list_agents read-onlyList saved voice Agent profiles before creating or changing one.
  • create_agentCreate a reusable voice Agent profile: persona, greeting, voice, language, tools and knowledge. Does not place a call. Use saved tool IDs; configure connection settings privately in the PyAI console. Never supply credent
  • get_agent read-onlyRead a saved voice Agent profile and its current configuration.
  • update_agentUpdate a voice Agent profile. Read it first and change only user-requested fields. Use saved tool IDs; configure connection settings privately in the PyAI console. Never supply credentials.
  • set_agent_toolsReplace the tools bound to an Agent. Read the current Agent first; this replaces its bindings. Use saved tool IDs; configure connection settings privately in the PyAI console. Never supply credentials.
  • set_agent_knowledgeReplace the knowledge bases bound to an Agent. Read its existing bindings first.
  • get_trace_config read-onlyInspect Trace call-compliance configuration.
  • configure_traceConfigure Trace compliance monitoring for the selected workspace.
  • list_trace_rule_packs read-onlyDiscover available Trace compliance rule packs before enabling monitoring.
  • create_trace_rule_packCreate a workspace Trace compliance rule pack. This creates persistent configuration.
  • list_trace_interactions read-onlyFind monitored calls and interactions for compliance review.
  • get_trace_interaction read-onlyRead one monitored interaction and its compliance evidence.
  • list_trace_findings read-onlyFind compliance findings with source evidence. Findings are signals for review, not legal conclusions.
  • list_trace_violations read-onlyList Trace rule violations for compliance review.

…and 15 more.

Connect it

Claude Code
claude mcp add --transport http pyai-voice-ai https://api.pyai.com/mcp
Claude.ai / ChatGPT
Settings → Connectors → Add custom connector
URL: https://api.pyai.com/mcp
Cursor (~/.cursor/mcp.json)
{
  "mcpServers": {
    "pyai-voice-ai": {
      "url": "https://api.pyai.com/mcp"
    }
  }
}
VS Code (.vscode/mcp.json)
{
  "servers": {
    "pyai-voice-ai": {
      "type": "http",
      "url": "https://api.pyai.com/mcp"
    }
  }
}

Questions

What does PyAI Voice AI do?

Speech, transcription, voice agents, Trace, Recap, dubbing and narration with browser OAuth. It exposes 55 tools to AI assistants.

What tools does PyAI Voice AI provide?

55 tools, including openapi_get, get_started, whoami, list_models, list_voices, synthesize_speech, create_transcription_job, get_transcription_job, configure_amd, list_amd_calls, get_amd_call, enable_recap….

How do I connect PyAI Voice AI to Claude, ChatGPT or Cursor?

Add the remote MCP endpoint https://api.pyai.com/mcp as a custom connector or MCP server. Copy-paste setup is on this page.

Does PyAI Voice AI require an account or API key?

No sign-in was needed to list its tools. Individual tools may still need an account or API key.

Is PyAI Voice AI online?

As of 2026-11-19 our probe found it online. It answered 100% of our last 3 checks.

Who publishes PyAI Voice AI?

@atomsai on GitHub. The official MCP Registry verified that the publisher controls this GitHub account before accepting the listing.

Similar in Audio, Voice & Music