FreeTTS is an MCP server with 8 tools an agent can call, among them batch_text_to_speech, check_usage, dialogue_to_speech. It answers at https://mcp.freetts.org/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 4 of 4 times since 30 September 2026; the last check, on 16 November 2026, succeeded.
Text to speech in 149 languages: MP3 links from any assistant. Free without an account.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
batch_text_to_speech | Make one audio file per text from a list, in one call: vocabulary and flashcards, quiz questions and answers, H5P and other e-learning clips, app or game lines, each line of a dialogue as its own file. Up to 50 texts of up to 1,000 characte Inputs: texts, voice, voices, language, speed, format |
check_usage | Show the FreeTTS plan behind this connection and what is left: characters today or this month, requests a minute, HD voices, watermark. Use it when the user asks about limits, their plan, or why a request was refused. |
dialogue_to_speech | Turn a script with several speakers into one audio file, a different FreeTTS voice per speaker, with a pause between lines. Write each line as 'Name: text'. Use it for two-host shows, interviews, scenes, language lessons with two speakers. Inputs: script, voices, pause_ms, language |
list_voices | List FreeTTS voices for a language or a search word, with the voice id to pass to text_to_speech. Says which voices are free and which need a FreeTTS PRO key (HD and Signature). Use it when the user names a language, accent or gender, or as Inputs: language, search, gender, free_only, limit |
script_to_tracks | Record a script with exact timing, the way FreeTTS Script mode does: (pause 2) is exactly 2 seconds of silence, (beep), (ding) and (click) play a sound, 'CUE:' lines are read in a second voice, 'TRACK: name' starts a new audio file, 'NAME: Inputs: script, line_voice, cue_voice, speed, sentence_pause_ms, paragraph_pause_ms |
suggest_voice | Suggest three FreeTTS voices for a language and a use (audiobook, tutorial, ad, news, children's story, meditation, podcast), with a short reason each. Use it when the user has not named a voice. Inputs: language, use, gender |
text_to_speech | Convert text to spoken audio with a FreeTTS voice and return a download link to the MP3 (or WAV with a FreeTTS PRO key). Use it when the user wants text read aloud, narrated, or saved as an audio file. Without a FreeTTS key: standard voices Inputs: text, rerender_of, voice, language, speed, format |
transcribe_audio | Turn a recording into text with FreeTTS speech to text. Give a public https URL to an audio file (mp3, wav, m4a, ogg, webm). Needs a connected FreeTTS PRO account. Inputs: audio_url, language |
Every block below points at https://mcp.freetts.org/mcp. Pick your client and copy.
claude mcp add --transport http freetts https://mcp.freetts.org/mcp
{
"mcpServers": {
"freetts": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.freetts.org/mcp"]
}
}
}{
"mcpServers": {
"freetts": {
"url": "https://mcp.freetts.org/mcp"
}
}
}{
"servers": {
"freetts": {
"type": "http",
"url": "https://mcp.freetts.org/mcp"
}
}
}{
"context_servers": {
"freetts": {
"url": "https://mcp.freetts.org/mcp"
}
}
}{
"mcpServers": {
"freetts": {
"serverUrl": "https://mcp.freetts.org/mcp"
}
}
}{
"mcpServers": {
"freetts": {
"url": "https://mcp.freetts.org/mcp"
}
}
}name: FreeTTS
version: 0.0.1
schema: v1
mcpServers:
- name: FreeTTS
type: streamable-http
url: https://mcp.freetts.org/mcp{
"mcpServers": {
"freetts": {
"httpUrl": "https://mcp.freetts.org/mcp"
}
}
}{
"mcpServers": {
"freetts": {
"type": "http",
"url": "https://mcp.freetts.org/mcp"
}
}
}{
"mcpServers": {
"freetts": {
"url": "https://mcp.freetts.org/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fmcp.freetts.org%2Fmcp&type=streamable_http&id=freetts&name=FreeTTS
It answered our last check on 16 November 2026 in 177 ms. Over 4 checks since 30 September 2026 it answered 4. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by freetts.org and served from mcp.freetts.org, the vendor's own domain: https://mcp.freetts.org/mcp.
8, as returned by the server's own tools/list on 18 November 2026: batch_text_to_speech, check_usage, dialogue_to_speech, list_voices, script_to_tracks, suggest_voice, text_to_speech, transcribe_audio.
It answered our last check on 16 November 2026 in 177 ms. Over 4 checks since 30 September 2026 it answered 4.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://mcp.freetts.org/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: org.freetts. Endpoint host: mcp.freetts.org. ARD identifier: urn:air:org.freetts:mcp:mcp.
First indexed 30 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.