Endpoints: 76,849MCP servers: 32,723Payout addresses: 3,825Paid calls: 6,104Letters: 83Defects: 3,890counted 3 min ago
teppi

MCP serverio.github.Nutshell2000/agent-data-tools-voice

Transcribe audio and video (SRT/VTT subtitles, an hour for $0.05) and text to speech as MP3.
UNRATEDActivestreamable-httpagent-data-tools.revmesh2074.workers.dev

Overview

Score?
UNRATED 0.143
of what a free look can see, on 2 looks
Looks
2
last 17 hr ago
Tools
10
changed 17 hr ago

More info

URL
agent-data-tools.revmesh2074.workers.dev/mcp/voice
streamable-http
Says it is
agent-data-tools 1.219.0
protocol 2025-06-18
In the record since
2 days ago

Among servers32,723 with a card

0median 0.547 · this server 0.143 · highest on record 0.8351

Toolsfrom sha256:caa04a7884…834138 · +2 −2 17 hr ago

The tools this server lists, read out of the definition it returned
ToolSchema
dialogue added
Turn a script into a multi-voice conversation: write one line per turn as "Name: text", each speaker gets their own natural voice (Deepgram Aura-2, English or Spanish, or pick voic
input · no output
dub
Dub a clip: speech in any of 90+ languages is transcribed, translated and spoken again, with translated SRT on the original timings. New voice in English or Spanish (Aura-2 MP3, pi
input · no output
subtitles_translate
Translate an SRT or WebVTT subtitle file into another language cue by cue, keeping every timing and the file format, so the result drops straight into a video player or editor. Up
input · no output
text_to_speech
Text to speech for a paragraph or a page: up to 2,000 characters as one MP3 in English (40 voices) or Spanish (10 voices) with Deepgram Aura-2, or up to 1,200 characters as one WAV
input · no output
text_to_speech_captions added
Text to speech that comes with subtitles: up to 2,000 characters spoken as one MP3 in English or Spanish (Deepgram Aura-2, pick a voice), plus SRT or VTT captions whose timings com
input · no output
transcribe
Transcribe speech from an audio file at a public URL, or uploaded in a POST body, using Whisper large-v3-turbo. Returns the transcript text, detected language, duration and word co
input · no output
transcribe_long
Transcribe a podcast, meeting, interview or lecture: up to 60 minutes of MP3 or WAV (25 MB) by URL or uploaded in a POST body, 90+ languages, Whisper large-v3-turbo. Parts are join
input · no output
transcribe_speakers
Transcribe a meeting, interview, call or podcast with speaker labels: each turn says which speaker talked, with start and end times (Deepgram Nova-3). MP3/WAV up to 15 minutes, oth
input · no output
transcribe_summary
Summarize a voice note, meeting, call or podcast in one call: transcribes up to 60 minutes (MP3/WAV up to 25 MB; M4A, OGG or WebM up to 5 MB) by URL or upload, then returns a title
input · no output
voice_agent
One turn of a voice assistant: send the user's voice note (or text), your instructions and the earlier turns; get back what was heard, a short reply, the reply spoken in English, S
input · no output
ai_speech removed
Turn up to 300 characters of text into natural, human-sounding speech as an MP3 (base64), in English (40 voices) or Spanish (10 voices), with Deepgram Aura-2. Pick a voice by name
—
text_to_speech_lite removed
Low-cost text to speech for longer English text: up to 2,000 characters as one MP3 (base64) with Deepgram Aura-1, 12 voices. Half the price per character of text_to_speech, with a
—
Verify it yourselfnpx teppi-check https://agent-data-tools.revmesh2074.workers.dev/mcp/voicecurl -s https://api.teppi.xyz/v1/trust/mcp/mcs_01M7HEEK1183NBTD2P8D2F5961