Actionist·Async
Async

Async

· #327 most-used

Human-like AI voices for agents, content, and real-time voice experiences

MarketingCommunicationProductivityDeveloperAIAutomation

Async is the AI voice platform (formerly Podcastle) that converts text into human-like speech for agents, content creators, and real-time voice applications. Its API delivers text-to-speech in 15+ languages with about 300 ms latency, instant voice cloning from a 3-second audio sample, and 500+ unique voices. Connect it to Actionist and your agents can narrate reports, produce multilingual audio assets, power real-time voice interactions via streaming, and generate captioned audio with word-level timestamps — all without a voice actor or a recording studio.

Try Async with ActionistVisit Async
Average time saved
6 hours
per person · per month
≈ 1 workdays back

Eliminates manual work. Agents eliminate the manual cycle of coordinating voice actors, recording audio for reports and communications, and producing separate language versions for global teams.

Schedule

What your Async agent runs on autopilot

A week of scheduled jobs your Actionist agent will execute on your behalf.

28Scheduled jobs
7Agents at work
24/7Always on
Agents
Tue–Thu
Tue
Wed
Thu
7a
8a
9a
10a
11a
12p
1p
2p
3p
4p
5p
6p
Multi-app workflows

Async × every other app you use

End-to-end automations that span multiple apps — each one a real business outcome.

6Workflows
6Apps spanned
~18 hrsSaved / week
6Personas served
For operations
Featured4 apps

Ops report narrated and in Slack before the standup

When a new operations report is published in Notion, the agent selects the best professional voice from the library, narrates the report as an MP3, saves it to Google Drive, and posts the audio link with a short summary to the #operations Slack channel — all before the Monday morning standup.

~2 hrs

Time saved for your team — every week, on autopilot

The flow
Trigger·When a new weekly operations report is published in Notion
Trigger
Step 1
Notion
Detect new weekly operations report published
read
Step 2
Async
List voices to select the highest-quality professional voice
write
Step 3
Async
Generate speech to narrate the report as an MP3 audio file
write
Step 4
Google Drive
Save audio file to the operations reports folder
write
Step 5
Slack
Post audio file link to #operations with a 3-line summary
Result
Generate speech to narrate the report as an MP3 audio fileSave audio file to the operations reports folderPost audio file link to #operations with a 3-line summary
The win
Saved per run
20 min
Runs / week
~5×
Zero-screen briefing — team listens during commute
Driven byOperations Agent
ROI

Savings

What your team gets back — two angles: what you stop doing manually, and what that's worth.

Without Actionist

What you do manually today

With Actionist

What your agent runs for you

  • Sales
    30 min / week
    No audio versions of sales materials

    Sales teams write text-only proposals and hope prospects read them. There is no audio touchpoint, no differentiated delivery format, and no way to confirm the proposal was consumed.

    Sales Agent
    0 min
    Agent narrates proposals as audio before they send

    When a proposal is finalised in Notion, the agent generates a narrated audio summary using Generate speech with custom pronunciation and attaches it to the outbound email — prospects receive an audio walkthrough of the proposal that stands out in a crowded inbox.

  • Marketing
    60 min / week
    Blog posts have no audio version

    Marketing teams rely on readers engaging with text-only content. Audio production requires hiring voice actors, scheduling recording sessions, and editing — so audio versions of articles never happen.

    Marketing Agent
    0 min
    Agent auto-narrates blog posts in three languages

    Every published blog post is automatically narrated in English, French, and Spanish using locale-matched voices and saved to Google Drive — three audio assets per post, zero manual production work.

  • Customer Support
    25 min / week
    Templated text closure emails

    Support teams send templated email closures that customers often ignore. High-value accounts get the same generic resolution email as everyone else — no audio differentiation, no personalisation signal.

    Customer Support Agent
    0 min
    Agent generates personalised spoken ticket resolutions

    When a VIP ticket is resolved, the agent generates a personalised spoken summary using the customer's name and the resolution steps — delivered as an audio attachment in the closure email, making the interaction feel high-touch without additional headcount.

  • Human Resources
    40 min / week
    Text-only onboarding documents

    HR sends PDF handbooks and written policy documents that new hires are expected to read in full. Comprehension and engagement are low, especially for compliance content — and producing audio versions manually is impractical.

    Human Resources Agent
    0 min
    Agent delivers audio onboarding kit on hire

    When a new hire is added, the agent generates a personalised audio welcome message and a narrated compliance training module with chapter timestamps — the new hire receives a human-feeling audio experience before day one without HR recording anything.

  • Finance
    20 min / week
    Spreadsheet-dependent financial reviews

    Finance teams distribute spreadsheets and expect leaders to read them before meetings. Senior leaders often skip the review, misread figures, or rely on verbal summaries with no documentation — all avoidable with a narrated brief.

    Finance Agent
    0 min
    Agent narrates weekly financials as accurate audio briefs

    The agent generates a narrated weekly financial brief with custom pronunciation for all figures and the company name — the CFO hears accurate numbers before the Friday standup without reading a spreadsheet.

  • Operations
    20 min / week
    Written reports that engineers scan before meetings

    Operations teams publish written status reports that engineers skim in the 2 minutes before standup. Key details are missed, context is lost, and the same questions come up every week because nobody read the full report.

    Operations Agent
    0 min
    Agent posts narrated ops report to Slack before standup

    When the weekly operations report is published in Notion, the agent narrates it at 1.2× speed and posts the audio to #operations — engineers hear the full status brief in under 3 minutes while walking to the standup room.

  • Legal
    45 min / week
    English-only text regulatory summaries

    Legal teams distribute English-language regulatory summaries to all global offices. Non-native English speakers in EU entities miss nuances, translation takes days, and the compliance window often closes before in-market teams are properly briefed.

    Legal Agent
    0 min
    Agent narrates regulatory updates in English, French, and German

    When a regulatory update is added to Notion, the agent generates narrated versions in three languages for the relevant jurisdiction legal teams — each team hears the update in their language before the weekly legal review.

+ 100s of other Async automations
Average time saved
24 hrs / person / month
Calculator

Calculate what your team saves

Team size
5 people
Hourly rate
$75 / hr
Hours saved / week
8
Hours saved / year
375
Annual ROI
$28,125

Based on Async's typical team usage — the visible tasks plus a few other automations the agent runs: ~1.5 hrs / person / week of admin work automated.

Connect

How to plug Async into Actionist

Pick the connection method that suits your environment.

Authenticate with your Async API key — generated in the Async developer dashboard. Actionist passes it as the x-api-key header on every Voice API request.

1
Generate an API key in Async

Log in to async.com, navigate to the Developer section, and open API Keys. Click Create key and give it a descriptive name (e.g. 'Actionist').

2
Copy the key

Copy the API key immediately — it is only shown once. Store it securely; treat it like a password.

3
Paste into Actionist and test

Paste the key into the API key field below and click Test connection. Actionist will call the List voices endpoint to confirm the handshake.

Credentials you'll need
API key*
async.com → Developer Dashboard → API Keys → Create key
Actions

12 actions your agent can call

Read and write operations available to your Actionist agent.

Triggers

0 events your agent can react to

Events your agent watches for, and the actions it kicks off in response.

This app has no triggers yet.
MCP servers

MCP servers that work with Async

Connect Actionist to MCP servers built for or around this app.

mcp-arangodb-async

Async MCP server for ArangoDB: 46 tools for graphs, queries, and multi-tenancy.

FAQs

Questions about Async + Actionist

How does Actionist connect to Async?
Go to the Apps tab in Actionist, find Async, and click Connect. The recommended path is API key — navigate to your Async developer dashboard at async.com, generate an API key, and paste it into the API key field in Actionist. Actionist then runs a test call to list available voices and confirm the connection is live before any actions run.
What credentials does Actionist need to call the Async Voice API?
The Async Voice API uses an `x-api-key` header for authentication. All API endpoints require this header plus a `version` field (e.g. 'v1'). Your API key is scoped to your Async account and grants access to text-to-speech generation, voice listing, and voice cloning. Keep the key in Actionist's encrypted secrets store — do not paste it into plain-text workflow steps.
Which Async model should I use in my Actionist agent?
Async Voice API offers three model tiers: `async_pro_v1.0` (highest quality, English-only), `async_flash_v1.5` (low-latency streaming, 6 languages), and `async_flash_v1.0` (legacy, 15 languages). Flash models are best for real-time agent responses and interactive voice experiences where latency matters. Pro is best for content production, podcast narration, or any scenario where output quality outranks speed.
Can the Actionist agent use a cloned voice for text-to-speech?
Yes. Async supports instant voice cloning from a 3-second audio sample. Upload the sample via the Async platform to generate a custom voice with a unique `voice_id`. That voice ID can then be passed to any text-to-speech action in Actionist — enabling agents to narrate content in a consistent brand voice or a specific team member's voice across all automated audio outputs.
What are the most common things agents do with Async?
The most common patterns with Actionist: (1) auto-narrate — whenever a report, update, or alert is generated in a connected app, the agent calls Generate speech to turn it into an audio file and posts it to Slack; (2) voice agent responses — integrate streamed TTS into a voice pipeline so the agent speaks back to callers in real time; (3) multilingual audio — send text in one language and specify a target language, and Async synthesises native-quality speech for that locale; (4) podcast production — when new blog content is published, the agent generates a narrated audio version and uploads it to a hosting platform.
When should I use streaming versus standard text-to-speech in Actionist?
For streaming use cases (voice agents, real-time IVR, conversational AI), use the WebSocket endpoint via Generate speech (stream) — it starts playing audio within about 300 ms of the first text chunk. For batch use cases (report narration, podcast episodes, training content), use the standard HTTP endpoint via Generate speech — it returns a complete audio file and supports higher quality models. The Timestamps variant is useful when you need to sync captions or lip animations to the audio.
Which languages does Async support, and how do I set the language in Actionist?
Async supports 15+ languages across its voice library including English, French, Spanish, German, Italian, Portuguese, Dutch, Arabic, Russian, Romanian, Japanese, Hebrew, Armenian, Turkish, Hindi, and Chinese. Language support varies by model tier: `async_pro_v1.0` is English-only, `async_flash_v1.5` covers 6 languages, and `async_flash_v1.0` covers 15 languages. Specify the ISO 639-1 language code in the `language` field when calling the action.
Is Async secure enough for sensitive business content like legal or HR documents?
Async has enterprise-grade security: SOC 2 compliance, GDPR compliance, a privacy-first data policy (your content is excluded from model training), and a 99.9% uptime SLA. Audio outputs generated via the API are not stored by Async after delivery. If your use case involves sensitive content such as legal documents, financial disclosures, or HR communications, Async's privacy guarantees make it suitable for production use inside Actionist agents.