Lets an assistant use Bambara text-to-speech, translation and audio transcription.
What you can do
Offers four tools: listing the Bambara voices available to the account with their identifiers, names and genders; converting text to audio with a chosen Bambara voice; translating text between Bambara and 13 other languages using language codes that combine language and script (for example bam_Latn, fra_Latn, eng_Latn); and transcribing an audio or video file from a public HTTPS URL with automatic language detection.
When to use it
Use it when an assistant needs to work with Bambara: producing Bambara speech, translating between Bambara and other languages, or turning a public audio or video link into text. It adds little if the work involves only mainstream languages or no speech and transcription.
Requirements
A remote endpoint plus an API key sent as a bearer token in the Authorization header, created in the Kooma console. The transcription tool needs the audio or video to be reachable at a public HTTPS URL and no larger than 25 MB.
Before you install
An API key is required in the Authorization header, so keep it private. Transcription fetches the file from a public URL, which is sent to a third-party service along with its content; avoid links to sensitive material. Text sent for speech or translation also goes to the remote service.
Connect Authorization token credentials. They are stored privately and never shown on public pages.
Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/ai.kooma%2Fkooma/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.
Liste les voix bambara disponibles pour la synthese vocale, avec leur identifiant, leur nom et leur genre. A appeler avant kooma_text_to_speech : les identifiants varient d'un compte a l'autre et ne doivent jamais etre codes en dur.
Takes no parameters.
kooma_text_to_speech
Transforme un texte en audio avec une voix bambara. Renvoie l'audio. Utiliser kooma_list_voices pour obtenir un identifiant de voix valide.
Parameterstextrequiredvoicerequiredformat
kooma_translate
Traduit un texte entre le bambara et 13 autres langues. Les codes de langue combinent langue et ecriture : bam_Latn (bambara), fra_Latn (francais), eng_Latn (anglais), et ainsi de suite.
Parameterstextrequiredsourcetargetrequired
kooma_transcribe_from_url
Transcrit en texte un fichier audio ou video accessible par une URL publique en HTTPS. La langue est detectee automatiquement. Le fichier est plafonne a 25 Mo.
Parametersurlrequired
Version history
1
v1.0.0LatestSep 16, 2026
Score
83%
83% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
Reached in the last 30 daysRequired25 pts
Auth declaredRequired10 pts
Tools listedRequired15 pts
DescriptionRequired15 pts
Logo10 pts
Documentation15 pts
Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.
LicenseNot applicable
A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.