Tapra MCP server
OfficialOne-line summary: Tapra is a local stdio MCP server that transcribes, subtitles, translates, and voices Tunisian Derja (mixed with French, English and Arabizi) media using your Tapra API key, plus free local ffmpeg audio editing.
Transcribe audio or video to txt/srt/vtt (+json with word timings), with free speaker detection, per-speaker clips, talk times, quotes and a
speakers.htmlreport; long files auto-chunked.Subtitle videos in one call (srt + vtt + txt), readable cue lengths, speaker colors, optional burned-in MP4.
Name speakers found in a transcript, assign colors, merge labels with the same name, rewrite subtitles, optionally burn them in.
Diarize only (who spoke when, no transcript).
Text to speech in Derja/Arabizi/French/English with Tapra voices, inline effect tags (
[euh],[breath],[stutter]…), speed 0.7–1.3,full/flashquality, and 19 audio formats.Create voiceovers from a script, line list, or SRT (dubbing with
timing: fit), producing a track, per-line clips andmanifest.json; can lay the result onto a video with original audio ducking.Translate text or whole SRT/VTT files between Derja, English, French and MSA, preserving timings and speaker labels; list supported languages.
Convert script between Arabizi and Arabic script (either direction).
Find in transcript when a word or phrase is said, with fuzzy/orthographic matching, for cutting clips.
Edit audio locally with ffmpeg: join, trim, remove silences, normalize loudness (−14/−16/−23 LUFS), fades, channel and format conversion — no charge.
Play audio on the local machine's speakers, and stop playback.
Free helpers: API status/health, model prices, output folder and ffmpeg check; balance, spend and last 10 charges; current voice list (also answers voice-cloning questions).
Safety/cost controls: per-call cost estimates with
TAPRA_MAX_COST_TNDcaps,max_cost_tndonly lowered by tools, path sandboxing (base/output dirs, hidden-folder blocking), no overwrites, and idempotency keys to avoid double billing.
Uses ffmpeg for local media processing: splitting long files into chunks and estimating their cost, burning subtitles into MP4s, converting generated audio between formats (mp3, opus, ulaw/alaw) and writing PCM WAV, editing audio (join, trim, silence removal, loudness normalization, fades), and playing audio files via ffplay.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Tapra MCP server Subtitle interview.mp4 with speaker labels, then translate the subtitles to French"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Tapra MCP server
Setup guide for every app: tapra.tn/mcp · API reference: tapra.tn/docs
Use Tapra from Claude Desktop, Claude Code, Cursor, or any MCP client: transcribe Tunisian Derja mixed with French and English, subtitle videos, generate speech and voiceovers, and convert between Arabizi and Arabic script.
The server runs locally over stdio. It reads your media files, calls the Tapra API with your key, and writes results to your output folder. Calls are billed like the API, and every paid tool reports its cost and your remaining balance.
Setup
Create an API key at https://tapra.tn/dashboard.
Install ffmpeg (needed for video, long-file chunking and cost estimates on audio):
winget install Gyan.FFmpeg,brew install ffmpeg, orapt install ffmpeg.Add the server to your client.
Claude Desktop / Cursor (claude_desktop_config.json or .cursor/mcp.json):
{
"mcpServers": {
"tapra": {
"command": "npx",
"args": ["-y", "@tapra/mcp"],
"env": {
"TAPRA_API_KEY": "tapra_sk_live_…",
"TAPRA_OUTPUT_DIR": "~/Tapra"
}
}
}
}Claude Code:
claude mcp add tapra -e TAPRA_API_KEY=tapra_sk_live_… -- npx -y @tapra/mcpRelated MCP server: video-summarizer
Tools
Tool | What it does | Billed |
| API health, models, prices, balance, output folder, ffmpeg check | free |
| Balance, total spent, and the 10 latest charges for your key | free |
| The Tapra voices and what each sounds like | free |
| Transcribe audio or video: one folder with txt, srt and vtt (+ json), speakers detected and colored, a clip of each voice and a | per minute |
| Subtitles for a video (srt + vtt + txt in one call), readable cue lengths, speaker colors, optional burned-in MP4 | per minute |
| Name the detected speakers (and pick colors); rewrites txt/srt/vtt, merges labels given the same name, can burn the result | free |
| Who spoke when, without a transcript | per minute |
| Speak Derja / Arabizi / French / English with a Tapra voice, effect tags, 19 formats | per character |
| Narration from a script, or dubbing from an SRT, on one timeline; writes the track, per-line clips and | per character |
| Play a file on this computer's speakers (or stop playback) | free |
| When is a word or phrase said? Word-level times from a JSON transcript | free |
| Join, trim, remove silences, normalize loudness, fade, convert | free |
| Arabizi ↔ Arabic script | per character |
Example prompts:
"Subtitle ~/Videos/interview.mp4 with speaker labels and burn them in."
"Write a 30-second Derja ad for a coffee shop, then make a voiceover with a warm female voice."
"Narrate this script with Zeineb, then lay it onto ~/Videos/promo.mp4."
"Where does she say 'el budget' in interview.json? Cut 5 seconds around it and normalize to -14 LUFS."
Voices
Voice | Sounds like |
| Man. The default. |
| Woman. A warm storyteller, made for narration. |
| Man. Calm. |
| Woman. Clear. |
| Man. Clear. |
| Woman. |
| Man. |
| Woman. |
| Man. |
| Woman. |
| Man. |
Speech is always pronounced the Tunisian way (loanwords and Arabizi). Effect tags go inline
and are not billed: [euh] hesitation, [aaa] long filler, [hmm], [ahem] throat clear,
[ouf] sigh, [breath] out-breath, [stutter] (right before the word to stutter), e.g.
"[euh] ma na3rafch, [breath] khalli nchouf". Unknown tags are refused before any charge.
list_voices reads the current list from the API (GET /v1/voices), so voices added on the
server work without updating the MCP; the table above is the built-in copy used when the API
cannot be reached. quality: "flash" uses the same voices about 5x faster and cheaper. Voice cloning is not
currently available; the server tells the model so, and it should offer these voices instead.
Audio formats
format on text_to_speech, create_voiceover and edit_audio: wav (default, lossless) or one of
the 18 ElevenLabs-style formats: mp3_22050_32, mp3_44100_32/64/96/128/192,
pcm_8000/16000/22050/24000/44100 (16-bit WAV at that rate), ulaw_8000 / alaw_8000
(G.711 telephony, in WAV), opus_48000_32/64/96/128/192 (Ogg Opus). pcm needs nothing extra;
mp3, opus, ulaw and alaw need ffmpeg.
Progress
speech_to_text, transcribe_video, create_voiceover and edit_audio
send MCP progress notifications (per chunk, line or batch) when the client asks for them, so long
jobs show progress and do not time out.
Voiceover manifest
create_voiceover writes a folder you can hand to a video tool:
voiceover_20261027-142233-a1b2/
voiceover.wav full narration
manifest.json { duration, segments: [{ index, text, start, end, clip }] }
clips/001.wav … one clip per lineWith srt_path, timing: "fit" asks the model to make each line last as long as its subtitle,
which is what dubbing needs. timing: "natural" keeps natural pacing and warns when a line
spills into the next one.
Configuration
Variable | Default | Meaning |
| required | Your |
| read from tapra.tn | Force an API origin. Must be |
|
| Website serving the price list, balance, and the current API address |
|
| Where generated files go; outputs can't be written anywhere else |
| home folder | Input files must be inside this folder; relative paths resolve here. Hidden folders/files ( |
|
|
|
|
| Largest file returned inline in |
|
| Refuse any single call estimated above this many TND. Only you can raise it; a tool's |
| off |
|
|
| Path to ffmpeg if it is not on |
|
| Per-request timeout |
| ffplay, then the system player | Program |
Without TAPRA_API_URL, the server asks TAPRA_SITE_URL/api/openapi for the current API
address, so moving the model host needs no client change. Only an https:// address on
tapra.tn or a subdomain is accepted (your key is sent there); anything else falls back to
https://api.tapra.tn.
Spending: every paid call is estimated first and refused above TAPRA_MAX_COST_TND
(20 TND per call when unset, about 2 h of transcription). The model can pass max_cost_tnd
to ask for a lower cap, never a higher one. Audio length is measured on the extracted audio,
not the file header, and extraction stops at the length the cap pays for. When no estimate is
possible (price list unreachable, or ffmpeg missing so the length is unknown) the call is
refused unless TAPRA_ALLOW_UNESTIMATED=1.
File safety: inputs outside TAPRA_BASE_PATH (including through symlinks) and outputs
outside TAPRA_OUTPUT_DIR (including through symlinks or junctions) are refused. Tools that
work on results, like play_audio and edit_audio, also accept files in the output folder or
tapra://output/... URIs. Inside the base folder, hidden folders and files (any path part
starting with ., such as .ssh or .aws) and AppData / Library directly under it are
refused too, checked on the real path and ignoring case. An existing file is never replaced (take.wav
becomes take-1.wav). A missing input gets "did you mean" suggestions from the same folder.
Every file a tool makes can be re-read as an MCP resource, tapra://output/<path>.
Every paid call sends a fresh Idempotency-Key, so automatic retries are never charged twice.
Files longer than 15 minutes are split into chunks; with speaker labels on, labels restart in
each chunk (prefixed c1-, c2-, …).
Development
npm install
npm test # builds, then runs the unit, path-safety and end-to-end tests against a mock API
npx @modelcontextprotocol/inspector node dist/index.jsTests need Node.js 22+ and ffmpeg (video and long-file tests are skipped without it). They never call the real Tapra API.
Issues and pull requests are welcome. For questions about your account or billing, write to contact@tapra.tn.
License
MIT. The server is open source; the Tapra models it calls are a paid API.
Available Tools
16 toolsconvert_scriptArabizi ↔ ArabicA
Convert Tunisian text between Arabizi (Latin letters and digits, e.g. "3aslema, chna7welek?") and Arabic script, in either direction. Costs money per character.
Inputs: text (required), direction (required), max_cost_tnd.
create_voiceoverCreate a voiceoverA
Turn a script or a subtitle file into one narration track for video work. Each line is spoken with the same Tapra voice (amal = Mature woman. Warm, grounded, everyday Tunisian.; salma = Younger woman. Lighter and brighter, conversational.; salah = Man with a big, sharp (aigu) voice that carries. Strong presence.; fahmi = Middle-aged man. Normal, natural male voice.; leo = Young man. Light and energetic. The default Tapra voice.; voice cloning is not available) and placed on a timeline: at its subtitle time (from srt_path) or one after another (from script or lines). Lines may use effect tags ([euh] breathy hesitation; [aaa] long filler while thinking; [hmm] closed-mouth "mmm"; [ahem] clears the throat; [ouf] tired sigh; [breath] out-breath, "haah"; [stutter] repeats the first sound of the next word; put it right before that word). Writes a folder with the voiceover track (wav or another format), one WAV clip per line, and manifest.json (text + start/end per clip) that video generation tools can follow. Optionally lays the voiceover onto a video. Reports progress per line. Costs money per character.
Inputs: lines, speed, voice, format, +10 more.
diarize_audioWho spoke whenA
Find speaker turns in an audio or video file (no transcript). Returns each turn with its speaker and times. Costs money per minute.
Inputs: input_path (required), output_path, max_cost_tnd.
edit_audioEdit audioA
Prepare audio for videos and posts, locally with ffmpeg: join several files in order, trim, remove long silences, normalize loudness (-14 LUFS for social video, -16 podcasts, -23 broadcast), fade in/out, and convert to any of the 19 formats. Video inputs contribute their sound. Writes a new file; never changes the originals. Free.
Inputs: input_paths (required), format, channels, trim_end, +8 more.
find_in_transcriptFind in transcriptARead-onlyIdempotent
Find when a word or phrase is said, with timestamps, in a transcript saved by speech_to_text or transcribe_video (.json gives word-level times; .srt/.vtt give subtitle-level times). Matches Arabic script with or without harakat and letter variants (أ/ا, ة/ه, ى/ي), French accents optional, and small typos when fuzzy. Useful for cutting video ("where does he say X?"). Free, runs locally.
Inputs: query (required), transcript_path (required), fuzzy, max_results.
get_balanceBalance and usageARead-onlyIdempotent
Show the Tapra balance (TND), total spent, and the 10 most recent charges for this API key. Free.
Inputs: no named parameters.
list_translation_languagesTranslation languagesARead-onlyIdempotent
List the languages translate accepts as source and target. Free.
Inputs: no named parameters.
list_voicesTapra voicesARead-onlyIdempotent
List the Tapra voices for text_to_speech and create_voiceover, with a description of each. Free. Also answers questions about voice cloning, which is not currently available.
Inputs: no named parameters.
name_speakersName speakersA
Give the speakers found by speech_to_text or transcribe_video real names (and optionally colors), then rewrite the txt, srt and vtt with those names. Each speaker keeps one subtitle color (srt colors, vtt voice styles). Labels given the same name are merged into one speaker. Free, works offline. Can also burn the named subtitles into the video.
Inputs: names (required), transcript_path (required), colors, formats, +2 more.
play_audioPlay audioARead-onlyIdempotent
Play an audio or video file on this computer's speakers (for example a clip you just generated). Returns right away while it plays; a new play stops the previous one. Set stop to just stop playback. Free.
Inputs: stop, input_path.
speech_to_textTranscribe audioA
Transcribe an audio or video file with Tapra, which handles Tunisian Derja mixed with French and English. One call writes a folder with the transcript as txt, srt and vtt (plus a .json with full timings). Speakers are labelled by default (no extra charge): the result says how many were detected, with talk time, a quote and an audio clip of each, and a speakers.html page. When there are several speakers, ask the user whether to name them, then call name_speakers. Long files are split into chunks automatically. Costs money per minute of audio.
Inputs: input_path (required), prompt, diarize, formats, +4 more.
tapra_statusTapra statusARead-onlyIdempotent
Check the Tapra connection: API health, available models, current prices, output folder, and whether ffmpeg is installed. Free. Call this first when a tool fails.
Inputs: no named parameters.
text_to_speechText to speechA
Speak text in Tunisian Derja (Arabic script or Arabizi), French, English, or a mix with one of the Tapra voices, with Tunisian pronunciation. Voices: amal = Mature woman. Warm, grounded, everyday Tunisian.; salma = Younger woman. Lighter and brighter, conversational.; salah = Man with a big, sharp (aigu) voice that carries. Strong presence.; fahmi = Middle-aged man. Normal, natural male voice.; leo = Young man. Light and energetic. The default Tapra voice.. Add non-verbal effects inline with tags (not billed): [euh] breathy hesitation; [aaa] long filler while thinking; [hmm] closed-mouth "mmm"; [ahem] clears the throat; [ouf] tired sigh; [breath] out-breath, "haah"; [stutter] repeats the first sound of the next word; put it right before that word. Example: "[euh] ma na3rafch, [breath] khalli nchouf". Saves the audio in the chosen format (wav by default, 18 other formats). Voice cloning and custom voice design are not currently available: if the user asks to clone a voice, say so and offer these voices. Costs money per character. For long scripts or narration timed to a video, use create_voiceover.
Inputs: text (required), speed, voice, format, +5 more.
transcribe_videoTranscribe video to subtitlesA
Make subtitles for a video: extracts the audio, transcribes Derja/French/English, and writes srt, vtt and txt in one go, timed for reading. Speakers are labelled and colored by default (no extra charge), with a speaker report and a clip of each voice; when there are several, ask the user whether to name them, then call name_speakers. Set burn_subtitles to also render a copy of the video with the subtitles drawn in. Needs ffmpeg. Costs money per minute.
Inputs: input_path (required), prompt, diarize, formats, +6 more.
translateTranslateA
Translate between Tunisian Derja and English, French, or Modern Standard Arabic (in both directions). Call list_translation_languages for the exact target names. Costs money per character.
Inputs: text (required), target (required), source, max_cost_tnd.
translate_subtitlesTranslate subtitlesA
Translate an SRT or VTT file between Tunisian Derja and English, French, or MSA, keeping every timing and speaker label. Lines are sent in batches to keep cost low. Pair with create_voiceover (srt_path) to dub a video. Reports progress per batch. Costs money per character.
Inputs: target (required), input_path (required), format, source, +2 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 16 tools
Most tools have clearly distinct purposes, and the descriptions explicitly disambiguate tricky pairs (translate vs translate_subtitles, text_to_speech vs create_voiceover). The main overlap is speech_to_text vs transcribe_video (which also accepts video input and transcribes it) and diarize_audio, since speech_to_text already labels speakers — an agent could hesitate over which to call for a video file.
Everything is snake_case and mostly verb_noun (list_voices, get_balance, create_voiceover, edit_audio, find_in_transcript). A few deviate into noun-ish or product-prefixed forms (speech_to_text, text_to_speech, tapra_status), but the set stays predictable and scannable.
16 tools is slightly above the ideal band but justified by the breadth of the domain (transcription, diarization, TTS, voiceover, translation, audio editing, diagnostics). No tool looks like pure filler, though diarize_audio comes closest since speech_to_text already returns speaker labels.
The surface covers a full media-localization lifecycle: status/balance, voice listing, STT, subtitles, speaker naming, diarization, TTS, voiceover, translation (text and subtitle files), script conversion, transcript search, playback, and ffmpeg editing. Minor gaps remain around discovering/managing previously generated output files or long-running jobs, which agents must work around by tracking paths themselves.
Maintenance
Related MCP Connectors
Transcribe, subtitle, dub and lip-sync media; create speech, voices, images and thumbnails.
Transcribe audio and video, and translate subtitles into 50+ languages.
Search, read, analyze and create HappyScribe transcripts and meeting notes from any MCP client
Bambara AI over MCP: text-to-speech, transcription and translation (Bamanankan + more).
Related MCP Servers
- AlicenseCqualityBmaintenanceMCP server that enables audio transcription from files (wav, mp4, mp3, flac) or microphone recording, with dynamic tool selection and enterprise-grade security.123MIT
- AlicenseNot gradedqualityDmaintenanceMCP server that converts videos, audio, and meeting recordings into structured transcripts and summaries with multi-backend ASR and automatic fallback.MIT

Equalang Translationofficial
AlicenseAqualityBmaintenanceTranslate PDF, Word (DOCX), Excel (XLSX) and PowerPoint (PPTX) files, images, subtitles and text. Turn audio and video into transcripts or translated subtitles. Preserve layout where supported. Requires an Equalang API key and credits.8100 npm22Apache 2.0- AlicenseAqualityBmaintenanceEnables MCP clients to use Arabic-centric AI for chat, cited Islamic Q&A, Qur'an and hadith quotation checks, deep research, Arabic-English translation, speech-to-text and text-to-speech, image generation, poetry, and safety moderation.12Apache 2.0