Best Alternatives to Kooma — Bambara AI

Frenchie

Runtime: npx

OCR, transcription, and image generation for AI agents via MCP.

Voicemode

Runtime: uvx

Natural voice conversations for AI assistants - STT/TTS via MCP

MCP Listen

Runtime: npx

Give your AI agents the ability to listen. Microphone capture and speech-to-text.

Transcription

Runtime: npx

AI transcription from URLs. 99% accuracy, speaker diarization, 98+ languages.

Kurdish (Sorani & Kurmanji) text-to-speech & speech-to-text — 664 AI voices. API key required.

MCP server for RiverScript, an AI transcription platform - fetches transcripts shared via a link.

Spoken

Runtime: npx

API to fetch published podcast transcripts as clean Markdown with real speaker names and timestamps.

Verbatim transcription of public video/audio URLs to clean text, SRT, and timestamped records.

CrispASR Agent Transcriber

Runtime: npx

Transcribe local audio and video with CrispASR and local models only.

Voice Audio MCP

Runtime: npx

Voice Audio MCP server. Tools: text to speech, list voices, transcribe. Built by MEOK AI Labs.

Speko

Runtime: npx

Official Speko MCP server: build, run, and migrate voice agents (STT/TTS/V2V) for coding agents.

Gilbert MCP

Runtime: npx

Gilbert meetings: list, search, and fetch transcripts & summaries via MCP.