Connect agent workflows to live voice conversations.
Before you connectCreate a Vapi account and API key, configure an assistant and authorized number or web calling, and approve recipients and spending.
Our integration playbook
Verify the business action separately from the conversation
Inspect setup, billing & access →Give your agent a phone connection and inspect call outcomes.
Before you connectConnect an existing Bland account or use agent onboarding with owner phone verification. Approve the calling scope and any payment or subscription.
Our integration playbook
Keep phone provisioning separate from payment completion
Inspect setup, billing & access →Generate speech and manage hosted voice agents.
Before you connectCreate or select an ElevenLabs workspace, authorize the connection and choose permitted voices, content and a usage budget.
Our integration playbook
Verify the audio artifact and the agent target independently
Inspect setup, billing & access →Transcribe audio through hosted speech models.
Before you connectCreate a Deepgram project, issue a scoped API key or sign in through the CLI, and choose an audio-processing budget and permitted input files.
Our integration playbook
Keep the transcript traceable to the original audio
Inspect setup, billing & access →Give agents API access to telephone and messaging infrastructure.
Before you connectCreate and fund a Telnyx account, issue a V2 API key and configure the numbers, messaging or voice resources required for your workflow. Complete applicable provider onboarding before production use.
Our integration playbook
Separate resource inspection from outbound communication
Inspect setup, billing & access →Run realtime voice agents on managed media and deployment infrastructure.
Before you connectCreate a LiveKit Cloud project, choose a plan, prepare a working agent and configure its secrets. Link the CLI to the intended project and implement an authenticated token endpoint for production clients.
Our integration playbook
Verify dispatch, media flow and shutdown as separate session states
Inspect setup, billing & access →Generate and transcribe speech through hosted voice models and agent tools.
Before you connectCreate a Cartesia account, select a usage plan and obtain server credentials or sign in through the MCP connection. Choose the voice, model and audio format required by the destination.
Our integration playbook
Match the audio contract before connecting speech to a live workflow
Inspect setup, billing & access →Turn recorded or live audio into transcripts through hosted speech models.
Before you connectCreate an account, obtain an API key and configure funds and alerts for the intended usage. Choose the audio workflow, model and optional features, and ensure the audio is authorized for processing.
Our integration playbook
Keep the audio job identity through transcription and downstream analysis
Inspect setup, billing & access →Stream audio and receive speaker-labelled transcripts and turn events for voice agents.
Before you connectCreate a Speechmatics account and API key, choose an approved processing region and fund the required usage. Configure the audio source and downstream agent separately.
Our integration playbook
Validate who spoke and when the agent should respond
Inspect setup, billing & access →Create and operate conversational video agents through API, MCP and CLI.
Before you connectCreate a Tavus developer account, configure credentials and billing, and choose a face, voice and permitted application tools. Set session duration, concurrency and spending limits.
Our integration playbook
Bound the session lifecycle before connecting application actions
Inspect setup, billing & access →Generate speech from text using hosted voice models and streaming audio APIs.
Before you connectCreate an account, choose a voice and usage plan, and issue a Standard API key. Obtain the necessary permission before using a custom voice.
Our integration playbook
Validate the audio stream before connecting it to a conversation
Inspect setup, billing & access →Generate talking-avatar videos from authorized images, footage and scripts.
Before you connectCreate an account and API key, choose an avatar workflow and confirm the plan’s usage licence. Custom Instant Avatars require a subject consent-verification recording and suitable training footage.
Our integration playbook
Separate content approval, rendering and publication
Inspect setup, billing & access →Deploy and scale voice-agent sessions on managed infrastructure.
Before you connectCreate an account and the intended organization, activate billing and configure the application’s model-provider secrets. Prepare an agent image or Dockerfile and choose deployment capacity and transport.
Our integration playbook
Test the full session lifecycle before scaling voice traffic
Inspect setup, billing & access →Transcribe recorded or streaming audio using hosted speech models and structured results.
Before you connectCreate a Soniox account and project, configure billing and generate a project API key. Choose the appropriate regional endpoint and recorded-file or live-streaming workflow.
Our integration playbook
Preserve audio evidence and job identity until the transcript is checked
Inspect setup, billing & access →