Integration

Freedom Speech integration

Freedom Speech is a speech AI service for Kazakh, Russian and English. Transcribe an audio file (the language is detected; optional speaker-labelled segments with the names you give), turn text into a 24 kHz WAV file in the built-in Tomiris or Taymas voice or a catalog voice, list the voices, download a catalog voice's preview sample and check that recognition is up. Not offered: the WebSocket streaming routes, and the translation, language detection (with its language list), voice cloning and voice design routes, which are served from freedomspeech.kz where keys from the console are not accepted. Authentication is an API key from console.freedomspeech.kz, sent in the X-API-Key header; the voice list, previews and health check need none.

Connect Freedom Speech How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Freedom Speech.Built from the 5 Freedom Speech tools below, on the connection you add once.

Common Freedom Speech use cases

transcribing a Kazakh or Russian voice message
voicing an answer in Kazakh for a Telegram bot
producing a Russian or Kazakh voice prompt
splitting a two-party call into agent and client turns

What you can do with Freedom Speech

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Each badge shows the default agent permission of an endpoint (allowed: an agent calls it without asking; ask first: you are asked before an agent calls it, when the agent or chat asks permission for sensitive actions; never: no agent may call it), which every user can change endpoint by endpoint in their credential settings.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Recognition health, 1 operation

get_recognition_healthGet recognition healthGETAgents: ask firstTells whether Freedom Speech's speech recognition is available: status is healthy when it is up; when it is down the service answers 503 with status unavailable. Needs no key; not cached, so call again to recheck.

Speech audio, 1 operation

create_speechCreate speechPOSTAgents: ask firstTurns text into speech and returns a WAV file (16-bit PCM, mono, 24 kHz). voice is tomiris, taymas or a catalog voice id from list_voices; the text's language is detected unless language is set.

Transcription, 1 operation

transcribe_audioTranscribe audioPOSTAgents: ask firstTranscribes an uploaded audio file (wav, mp3, ogg, oga, m4a, flac, webm, mp4, opus) and returns the text with its detected language and duration. response_format=diarized_json adds speaker-labelled segments.

Voice, 1 operation

list_voicesList voicesGETAgents: ask firstLists every Freedom Speech voice: id, display name and type (builtin or custom). Pass an id as voice to create_speech; custom catalog voices also have a preview sample (get_voice_preview). Needs no key.

Voice preview, 1 operation

get_voice_previewGet voice previewGETAgents: ask firstDownloads the pre-generated WAV preview sample of a custom catalog voice (id from list_voices). Built-in voices (tomiris, taymas) and voices whose preview is not generated answer 404. Needs no key.

Use Freedom Speech from Claude Code, Cursor or Codex

Connect Freedom Speech in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Freedom Speech operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Freedom Speech

Create your workspace
Sign up free. Nothing to install.
Connect Freedom Speech once
Add your Freedom Speech connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.

Freedom Speech integration FAQ

What can you do with the Freedom Speech integration?

LiveContext exposes 5 operations on Freedom Speech, covering recognition health, speech audio, transcription and voice. Common uses include transcribing a Kazakh or Russian voice message, voicing an answer in Kazakh for a Telegram bot and producing a Russian or Kazakh voice prompt.