"Fluent Bit" matching MCP servers:

Local voice toolkit over MCP: transcribe audio to text in 25 languages, synthesize speech in 9, and list available voices and languages. Runs fully on-device — no API keys, no cloud.

Enables AI clients to extract transcripts from specific Douyin, Xiaohongshu, and YouTube links, or from local media and subtitle files, with tools to check readiness, run extraction, and read paginated transcripts.

Enables AI assistants to transcribe local audio or video files on-device, with optional timestamps and cleanup, and to search locally stored dictation history without uploading audio or needing an API key. It also lets clients pre-download and verify the speech model before the first transcription.

Transcribe audio/video files using Groq-hosted Whisper with word-level timestamps, automatic caching, and cost estimation, offering up to 9x savings over OpenAI Whisper.

Enables generating finished MP3 podcast audio from scripts using local TTS engines, with configurable voices and speech speed, plus text-to-speech and voice listing tools.