{"id":"io.github.atomsai/pyai","slug":"io-github-atomsai-pyai","title":"PyAI Voice AI","description":"Speech, transcription, voice agents, Trace, Recap, dubbing and narration with browser OAuth.","version":"0.5.21","publisher":{"kind":"github","id":"atomsai","label":"@atomsai on GitHub","url":"https://github.com/atomsai"},"website":"https://pyai.com/mcp","repository":"https://github.com/atomsai/pyai-platform-backend","remotes":[{"type":"streamable-http","url":"https://api.pyai.com/mcp"}],"packages":[{"registryType":"npm","identifier":"@pyai/mcp","version":"0.5.21","runtimeHint":"npx","transport":{"type":"stdio"}}],"published":"2026-11-18","updated":"2026-11-18","status":"online","auth":"","latency_ms":964,"checked":"2026-11-19","uptime":100,"checks":3,"tools":[{"name":"openapi_get","title":"Openapi Get","description":"Fetch 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 key required.","read_only":true},{"name":"get_started","title":"Get Started","description":"Return 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 the official SDK.","read_only":true},{"name":"whoami","title":"Who Am I","description":"Introspect 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 and structuredContent. Names are display labels; verify IDs and environment too. Use verbose=true for key identity details. Use it before usage and to diagnose a 401/403/402.","read_only":true},{"name":"list_models","title":"List Models","description":"List the available PyAI models (catalog). No arguments.","read_only":true},{"name":"list_voices","title":"List Voices","description":"List PyAI stock + cloned voices. Optionally filter by gender or region. Use a returned voice id as the `voice` for synthesize_speech.","read_only":true},{"name":"synthesize_speech","title":"Synthesize Speech","description":"Generate 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 expiring resource_link, never a local file path. Host playback support varies. For integration code only, use get_started.","read_only":false},{"name":"create_transcription_job","title":"Create Transcription Job","description":"Submit an async speech-to-text job for an audio URL (https). Returns a job_id; poll with get_transcription_job. Supports diarization.","read_only":false},{"name":"get_transcription_job","title":"Get Transcription Job","description":"Get the status + result of a transcription job by id.","read_only":true},{"name":"configure_amd","title":"Configure AMD","description":"Set 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 realtime detection itself is a Twilio Media Streams WebSocket (wss /v1/amd/stream), a one-line-TwiML drop-in, not an MCP tool.","read_only":false},{"name":"list_amd_calls","title":"List AMD Calls","description":"List 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-level reason.","read_only":true},{"name":"get_amd_call","title":"Get AMD Call","description":"Get one PyAI AMD decision by call id (GET /v1/amd/calls/{id}): who/what answered, with the reason.","read_only":true},{"name":"enable_recap","title":"Enable Recap","description":"Enable 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.","read_only":false},{"name":"create_recap","title":"Create Recap","description":"Submit 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.","read_only":false},{"name":"get_recap","title":"Get Recap","description":"Read 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).","read_only":true},{"name":"list_recap_calls","title":"List Recap Calls","description":"List recent Recap records (GET /v1/recap/calls). Requires recap:read and Recap enabled.","read_only":true},{"name":"omni_list_calls","title":"Omni List Calls","description":"List Omni sessions, including inbound calls. Filter by session_label and preserve each returned call_id.","read_only":true},{"name":"omni_get_call","title":"Omni Get Call","description":"Read an Omni session's transcript, recording availability and summary. For outbound calls use artifacts.omni_call_id from calls_get.","read_only":true},{"name":"omni_get_summary","title":"Omni Get Summary","description":"Read the structured summary for an Omni call when generated; a missing summary is not an empty result.","read_only":true},{"name":"omni_get_transcript","title":"Omni Get Transcript","description":"Read the complete Omni call transcript through the authenticated API.","read_only":true},{"name":"omni_get_recording","title":"Omni Get Recording","description":"Get the canonical authenticated recording resource URL. Requires response=url. This URL is not public playable audio; recording must have been enabled.","read_only":true},{"name":"telephony_search_numbers","title":"Telephony Search Numbers","description":"Search available managed numbers and inspect provisioning requirements before purchase.","read_only":true},{"name":"telephony_list_numbers","title":"Telephony List Numbers","description":"List owned numbers and current Agent bindings before changing inbound routing.","read_only":true},{"name":"telephony_bind_number","title":"Telephony Bind Number","description":"Bind an owned number to an Agent using body.agent_id; null unassigns. Read existing bindings first. Changes inbound routing.","read_only":false},{"name":"telephony_create_call","title":"Telephony Create Call","description":"Place 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.","read_only":false},{"name":"calls_list","title":"Calls List","description":"List outbound calls and normalized network outcomes before retrying a dispatch.","read_only":true},{"name":"calls_get","title":"Calls Get","description":"Read the current state of an outbound call by returned ID. dispatch_unknown needs inspection, not another call. Recap and Omni recordings are separate resources.","read_only":true},{"name":"list_agents","title":"List Agents","description":"List saved voice Agent profiles before creating or changing one.","read_only":true},{"name":"create_agent","title":"Create Agent","description":"Create 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 credentials.","read_only":false},{"name":"get_agent","title":"Get Agent","description":"Read a saved voice Agent profile and its current configuration.","read_only":true},{"name":"update_agent","title":"Update Agent","description":"Update 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.","read_only":false},{"name":"set_agent_tools","title":"Set Agent Tools","description":"Replace 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.","read_only":false},{"name":"set_agent_knowledge","title":"Set Agent Knowledge","description":"Replace the knowledge bases bound to an Agent. Read its existing bindings first.","read_only":false},{"name":"get_trace_config","title":"Get Trace Config","description":"Inspect Trace call-compliance configuration.","read_only":true},{"name":"configure_trace","title":"Configure Trace","description":"Configure Trace compliance monitoring for the selected workspace.","read_only":false},{"name":"list_trace_rule_packs","title":"List Trace Rule Packs","description":"Discover available Trace compliance rule packs before enabling monitoring.","read_only":true},{"name":"create_trace_rule_pack","title":"Create Trace Rule Pack","description":"Create a workspace Trace compliance rule pack. This creates persistent configuration.","read_only":false},{"name":"list_trace_interactions","title":"List Trace Interactions","description":"Find monitored calls and interactions for compliance review.","read_only":true},{"name":"get_trace_interaction","title":"Get Trace Interaction","description":"Read one monitored interaction and its compliance evidence.","read_only":true},{"name":"list_trace_findings","title":"List Trace Findings","description":"Find compliance findings with source evidence. Findings are signals for review, not legal conclusions.","read_only":true},{"name":"list_trace_violations","title":"List Trace Violations","description":"List Trace rule violations for compliance review.","read_only":true},{"name":"get_trace_exposure","title":"Get Trace Exposure","description":"Read aggregate compliance exposure for the workspace.","read_only":true},{"name":"get_recap_config","title":"Get Recap Config","description":"Read Recap summarization configuration before changing it.","read_only":true},{"name":"get_cast_capabilities","title":"Get Cast Capabilities","description":"Discover Cast voices, emotions, formats and supported rendering capabilities.","read_only":true},{"name":"direct_cast_script","title":"Direct Cast Script","description":"Turn a narration script into directed Cast lines before rendering. Consumes usage.","read_only":false},{"name":"render_cast","title":"Render Cast","description":"Submit script text or directed lines using one top-level voice from get_cast_capabilities for the entire render. Per-line voices and a console project are not required or supported inputs. Returns a job; preserve its ID, poll get_cast_render and retrieve get_cast_audio when done. Consumes usage; do not resubmit on timeout.","read_only":false},{"name":"list_transcription_jobs","title":"List Transcription Jobs","description":"Find existing audio processing and transcription jobs before submitting duplicates.","read_only":true},{"name":"discover_tools","title":"Discover Tools","description":"Find the right PyAI tools and a short recipe for speech, STT, LiveKit or Pipecat integration, voice agents, compliance, summaries, dubbing or narration. No credentials or usage.","read_only":true},{"name":"get_dub_capabilities","title":"Get Dub Capabilities","description":"Read currently supported Dub input and output languages before submitting a translation.","read_only":true},{"name":"create_dub","title":"Create Dub","description":"Fetch audio from the user-authorized HTTPS source URL and start a translation and dubbing job. Accesses an external source and consumes usage. Keep job_id and poll get_dub_job; do not submit again after a timeout.","read_only":false},{"name":"get_dub_job","title":"Get dubbing job status","description":"Retrieve the status and available results of an existing dubbing job by job_id. This read does not start or repeat a job. Poll pending/processing states without resubmitting.","read_only":true},{"name":"get_dub_audio","title":"Get Dub Audio","description":"Retrieve completed dubbed audio as a playable result or download. Call only when get_dub_job reports done.","read_only":true},{"name":"get_cast_render","title":"Get Cast Render","description":"Check a durable Cast render job. Preserve the original job ID.","read_only":true},{"name":"get_cast_audio","title":"Get Cast Audio","description":"Retrieve completed Cast narration as playable audio or a download.","read_only":true},{"name":"preview_cast_line","title":"Preview Cast Line","description":"Generate one directed Cast line. Consumes usage. Check get_cast_capabilities for supported voice, emotion and intensity.","read_only":false},{"name":"transcribe_audio","title":"Transcribe Audio","description":"Transcribe a small audio attachment supplied as base64 (up to 8 MiB decoded). Returns the synchronous transcript without diarization controls. For word timestamps and speaker labels, use create_transcription_job with diarize=true for mono or channel=true for stereo, then get_transcription_job. Consumes usage.","read_only":false}],"server_info":{"name":"pyai","version":"0.5.21","title":"PyAI Voice AI","websiteUrl":"https://pyai.com/mcp"},"category":"audio-voice","tags":["agents","hr","browser"],"kind":"remote","source":"registry","submitted":{},"first_party":false,"domain_rank":null,"score":100,"indexable":true,"first_seen":"2026-09-08","stars":0,"badges":[],"sponsor":null,"page":"https://agentsindex.org/agents/io-github-atomsai-pyai/"}