CallFire API
✓ Official Vendor SpecCommunicationsVoice Telephonybasic123 EndpointsREST
For Agents
Run voice and SMS broadcasts, manage phone number inventory, retrieve call recordings, and handle inbound keywords through the CallFire V2 API.
Use for: I need to send an SMS broadcast to a list of contacts, Place an outbound voice call broadcast and track its progress, Retrieve the recording of a completed call, List all keywords my account has reserved
Not supported: Does not handle email delivery, push notifications, or video conferencing — use for voice broadcasts, SMS campaigns, and CallFire phone number inventory only.
CallFire is a voice and SMS communications platform that lets businesses run outbound dialer campaigns, send text broadcasts, manage phone number inventory, and process inbound responses. The V2 API exposes 123 operations across 90 paths grouped by calls, campaigns, contacts, keywords, media, numbers, orders, reports, texts, tickets, and webhooks. It supports broadcast lifecycle management (create, start, stop, archive), recipient batches, call recordings, text-to-speech sound generation, keyword opt-in handling, and account reporting. Authentication is HTTP Basic, which keeps integration simple for server-to-server callers.
Install Jentic One Beta
Connect the CallFire API to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the CallFire API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
1
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh2
Step 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
Capabilities
What an agent can do with CallFire API.
Run outbound voice broadcasts through /calls/broadcasts with start, stop, and archive lifecycle controls
Send and track SMS broadcasts via the /texts and /texts/broadcasts endpoints
Generate text-to-speech, file-based, and call-recorded sounds via /campaigns/sounds
Buy, list, and manage phone number inventory via /numbers
Retrieve call recordings as MP3 streams from /calls/{id}/recordings
Reserve and manage SMS keywords for inbound opt-in flows
Subscribe webhooks to receive inbound call and text events
Use Cases
Patterns agents use CallFire API for, with concrete tasks.
★ Outbound SMS Broadcast
Send a one-to-many SMS campaign by creating a text broadcast, attaching a recipient batch, and starting the broadcast. CallFire handles delivery, retries, and per-recipient status, and exposes broadcast stats through the broadcasts/{id}/stats endpoint so the agent can report send rate and reply rate back to the user.
POST a text broadcast with the message body, add a recipient batch, then POST to /texts/broadcasts/{id}/start and poll /texts/broadcasts/{id}/stats.
Voice Broadcast Dialer
Run a recorded voice broadcast or text-to-speech announcement to a contact list using /calls/broadcasts. The lifecycle endpoints — start, stop, archive, toggleRecipientsStatus — give the agent fine-grained control over a campaign in flight, and stats and call detail records are available through the broadcasts/{id}/calls and broadcasts/{id}/stats endpoints.
POST a call broadcast referencing a TTS sound, add recipients, and POST to /calls/broadcasts/{id}/start.
Inbound Keyword Capture
Reserve a short-code keyword via the /keywords endpoints so that inbound texts to a CallFire number trigger a workflow. Combined with webhook subscriptions on /webhooks, an agent can be notified the moment a user texts the keyword and respond with an SMS broadcast or a transactional reply.
Reserve a keyword via the /keywords endpoint and subscribe a webhook on /webhooks to be notified of inbound texts containing that keyword.
Call Recording Retrieval
Pull MP3 recordings of completed calls for QA or compliance review by calling /calls/{id}/recordings to list recordings then fetching /calls/{id}/recordings/{name}.mp3 for the audio. Useful for contact centres that need to surface a specific recording in a CRM ticket without storing audio in their own systems.
GET /calls/{id}/recordings to list recordings then GET /calls/{id}/recordings/{name}.mp3 and attach the audio file to the CRM record.
AI Agent Voice and SMS via Jentic
Through Jentic, an AI agent searches for an intent like 'send an SMS broadcast' and is returned the CallFire text broadcast operation along with its input schema. Because authentication is HTTP Basic, Jentic encrypts both the username and password fragments in the credential vault and assembles the Authorization header at execution time without exposing the raw values to the agent. Setup time is under an hour.
Use Jentic search for 'send an SMS broadcast', load the text broadcast schema, and execute it with the recipient list and message body.
Key Endpoints
123 endpoints — callfire is a voice and sms communications platform that lets businesses run outbound dialer campaigns, send text broadcasts, manage phone number inventory, and process inbound responses.
METHOD
PATH
DESCRIPTION
POST
/calls/broadcasts
Create a voice broadcast
POST
/calls/broadcasts/{id}/start
Start a voice broadcast
POST
/calls/broadcasts/{id}/stop
Stop a voice broadcast
GET
/calls/{id}/recordings
List recordings for a call
POST
/campaigns/sounds/tts
Generate a text-to-speech sound
GET
/numbers
List or search phone numbers
POST
/webhooks
Subscribe a webhook
POST
/calls/broadcasts
Create a voice broadcast
POST
/calls/broadcasts/{id}/start
Start a voice broadcast
POST
/calls/broadcasts/{id}/stop
Stop a voice broadcast
GET
/calls/{id}/recordings
List recordings for a call
POST
/campaigns/sounds/tts
Generate a text-to-speech sound
GET
/numbers
List or search phone numbers
POST
/webhooks
Subscribe a webhook
Why Jentic?
Three things that make agents converge on Jentic-routed access.
Credential isolation
CallFire uses HTTP Basic. Jentic stores both the API username and password encrypted in the vault and constructs the Authorization header at execution time, so the agent never holds either value in its prompt or context.
Intent-based discovery
Agents search Jentic by intent (for example 'send an SMS broadcast' or 'retrieve a call recording') and Jentic returns the matching CallFire operation along with its input schema, so the agent can call the right endpoint without reading the 90-path V2 reference.
Time to first call
Direct CallFire integration: 2-5 days for Basic auth wiring, broadcast lifecycle handling, recording fetch, and webhook receiver setup. Through Jentic: under 1 hour — search for the operation, load its schema, execute.
Related APIs
Alternatives and complements available in the Jentic catalogue.
FAQs
Specific to using CallFire API through Jentic.
What authentication does the CallFire API use?
The CallFire V2 API uses HTTP Basic authentication. The agent presents an Authorization header containing the base64-encoded API username and password issued in the CallFire dashboard. Through Jentic, those credentials are stored encrypted in the vault and assembled into the Authorization header at execution time.
Can I send a voice broadcast with the CallFire API?
Yes. POST a broadcast to /calls/broadcasts with the source sound (TTS, file, or call recording), add recipients via /calls/broadcasts/{id}/recipients, then POST to /calls/broadcasts/{id}/start to begin dialling. Stop it any time with /calls/broadcasts/{id}/stop.
How do I retrieve a call recording from CallFire?
List recordings for a call with GET /calls/{id}/recordings, then fetch the audio at GET /calls/{id}/recordings/{name}.mp3. The MP3 stream can be attached directly to a CRM ticket or stored in your own object store for retention.
What are the rate limits for the CallFire API?
The OpenAPI specification does not declare explicit per-endpoint rate limits. CallFire enforces account-level throughput tied to your plan and dialer concurrency — review your plan in the CallFire dashboard before scheduling large concurrent broadcasts.
How do I send an SMS broadcast through Jentic?
Run a Jentic search for 'send an SMS broadcast', load the text broadcast schema, and execute it with the recipient list and message body. Then load and execute the start broadcast schema. Install the SDK with pip install jentic and use the async search, load, and execute pattern.
Is the CallFire API free?
CallFire prices on a per-minute and per-text basis with monthly plans, plus per-phone-number rental fees. Pricing is set on callfire.com rather than declared in the spec — check the dashboard before launching a large campaign.
GET STARTED