org.freetts/mcp

Est-ce que org.freetts/mcp est sûr ?

Au dernier audit MCP Hub, le serveur MCP « org.freetts/mcp » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 7 outils

• check_usage≈ 130 tokens

  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.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "check_usage", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• dialogue_to_speech≈ 321 tokens

  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. Needs a connected FreeTTS PRO account.

  Paramètres, retour & exemple (4)

  Paramètres

  • script · string · requis
    Lines like 'Abd: Tonight we cook shakshuka.' one per line. Names before the colon.
  • voices · object · optionnel
    Speaker name to FreeTTS voice id, like {"Abd": "en-US-AndrewNeural", "Guest": "en-US-EmmaNeural"}. Unnamed speakers get a voice each.
  • language · string · optionnel
    Language of the lines when no voices are given.
  • pause_ms · integer · optionnel
    Silence between lines in milliseconds. Default 600.

  Exemple d'appel

  {"name": "dialogue_to_speech", "arguments": {"script": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_voices≈ 293 tokens

  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 asks what voices exist.

  Paramètres, retour & exemple (5)

  Paramètres

  • limit · integer · optionnel
    How many to return. Default 15.
  • gender · string · optionnel · female | male | any
    Filter by gender.
  • search · string · optionnel
    A word to match in the voice name or personality, like 'Andrew', 'calm' or 'news'.
  • language · string · optionnel
    Language or locale, like 'German', 'de-DE', 'Spanish (Mexico)' or 'en'. Empty lists every language.
  • free_only · boolean · optionnel
    Only voices that work without a FreeTTS key.

  Exemple d'appel

  {"name": "list_voices", "arguments": {"limit": 1, "gender": "female", "search": "texte", "language": "texte", "free_only": true}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• script_to_tracks≈ 553 tokens

  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: line' makes a scene with a voice per character. Returns one file with everything plus one file per track. Use it for ear prompter tracks, voiceovers timed to footage, rehearsal tracks, workout or recipe step audio. Needs a connected FreeTTS PRO account.

  Paramètres, retour & exemple (9)

  Paramètres

  • speed · integer · optionnel
    Percent slower or faster for the main lines. Default 0.
  • script · string · requis
    The script text. See freetts.org/text-to-speech-for-actors for the syntax.
  • my_part · string · optionnel
    In a scene, the character you play: their lines become timed gaps for you to say them.
  • count_in · string · optionnel · none | 3 | 5 | 10
    Spoken count-in before each track, one number a second. Default none.
  • cue_voice · string · optionnel
    Voice for CUE: lines and [bracketed] words. Default Aria.
  • track_end · string · optionnel · none | beep | end
    After the last line of each track: nothing, a long beep, or the word End. Default none.
  • line_voice · string · optionnel
    Voice for the main lines: a steady voice name or id (Guy, Andrew, Ava, Aria, Jenny, Brian, Emma, Sonia, Ryan, Libby, Natasha, William, Clara, Liam...). Default Guy.
  • sentence_pause_ms · integer · optionnel
    Silence after each sentence. Default 500.
  • paragraph_pause_ms · integer · optionnel
    Silence after each paragraph. Default 1000.

  Exemple d'appel

  {"name": "script_to_tracks", "arguments": {"script": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• suggest_voice≈ 206 tokens

  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.

  Paramètres, retour & exemple (3)

  Paramètres

  • use · string · optionnel
    What the audio is for, in a few words.
  • gender · string · optionnel · female | male | any
  • language · string · requis
    Language or locale, like 'English (US)', 'de-DE' or 'Portuguese (Brazil)'.

  Exemple d'appel

  {"name": "suggest_voice", "arguments": {"language": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• text_to_speech≈ 418 tokens

  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, up to 2,000 characters a call, a short spoken "FreeTTS" tag at the end, file kept one hour. With a key: the account's plan (PRO: HD and Signature voices, no tag, 10,000 characters a call, files kept 30 days).

  Paramètres, retour & exemple (6)

  Paramètres

  • text · string · requis
    The text to read. Plain text; SSML is not needed.
  • speed · integer · optionnel
    Percent slower (negative) or faster (positive). Default 0.
  • voice · string · optionnel
    A FreeTTS voice id from list_voices, like en-US-JennyNeural (a short name like 'Jenny' also works). If empty, a good standard voice for the language is chosen.
  • format · string · optionnel · mp3 | wav
    mp3 (default) or wav (FreeTTS PRO).
  • language · string · optionnel
    Language of the text when no voice is given, like 'German' or 'pt-BR'.
  • include_audio · boolean · optionnel
    Also return the audio bytes in the result (large). Default false; the link is enough for most clients.

  Exemple d'appel

  {"name": "text_to_speech", "arguments": {"text": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• transcribe_audio≈ 197 tokens

  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.

  Paramètres, retour & exemple (2)

  Paramètres

  • language · string · optionnel
    Language of the recording, like 'en-US', 'de-DE', 'Arabic' or 'es', or 'auto' to detect it (default).
  • audio_url · string · requis
    Public https URL of the audio file.

  Exemple d'appel

  {"name": "transcribe_audio", "arguments": {"audio_url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://mcp.freetts.org/mcp