Converts text to natural speech via Deepgram Aura. Returns a downloadable MP3 URL.
MIT
668,391 tools. Updated 2026-10-17 05:29
"Deepgram" matching MCP tools:
- Generate an MP3 audio version of a blog post using Deepgram text-to-speech. Saves the audio file and returns the download URL, while also sealing a ProofLink receipt for audit.MIT
- Transcribe audio from a URL or file path using Deepgram Nova-2. Get transcript, confidence score, word-level timestamps, and a sealed ProofLink receipt for verification.MIT
- Convert text to speech using Deepgram Aura, save the resulting MP3 file, seal a ProofLink receipt, and return the download URL.MIT
- Convert blog posts to MP3 audio with Deepgram TTS. Saves to blog-audio/ and returns the MP3 URL and filename, with a ProofLink receipt.MIT
- Transcribe audio from a URL or file path using Deepgram Nova-2, returning transcript, confidence, and word-level timestamps while sealing a ProofLink receipt.MIT
Matching MCP Servers
Deepgram MCPofficial
AlicenseNot gradedqualityDmaintenanceProvides AI editors with access to Deepgram's speech-to-text transcription and audio intelligence tools. Dynamically fetches available capabilities from Deepgram's API at runtime, ensuring access to new features without package upgrades.1MIT- AlicenseNot gradedqualityCmaintenanceEnables speech-to-text transcription, text-to-speech synthesis, and audio analysis using Deepgram's AI models. Supports features like speaker diarization, sentiment analysis, language detection, and various audio processing capabilities.2MIT
- Create a voice AI agent with just a name and instructions. Automatically applies provider defaults for brain, voice, and transcriber, enabling immediate deployment.MIT
- Creates a new AI voice agent for VoIP calls, configuring the LLM, TTS, and STT providers and system prompt.MIT
- Retrieve the complete source code for an SDK example, such as voice agents or call recording. Select from available examples to obtain implementation code.MIT
- Convert text to speech or generate prompt-based audio via OpenAI, Gemini, fal, or Cloudflare, then save the audio file to disk and return its path.MIT
- Initiate an outbound AI voice call. The AI agent follows your system prompt and speaks a first message when the recipient answers. Returns a call ID immediately; poll to get status, transcript, and summary.MIT
- Transcribe audio from a public URL into text using Deepgram Nova-3. Choose language, punctuation, and speaker identification; $0.10 per transcription.MIT
- Transcribes base64 audio using Deepgram, interprets intent with Gemini, and executes Splitwise expense actions from voice commands.MIT
- Transcribe a recording to text with a speech recognition model from the Hubris catalogue (Whisper, GPT-4o Transcribe, Deepgram, ElevenLabs Scribe and others). Same as POST /v1/audio/transcriptions with the audio sent as base64. Pass the file content itself, base64-encoded — links to files are not accepted. Every byte of the recording is written out inside this call, so it suits clips of seconds, not minutes; send longer recordings through the HTTP API (POST /v1/audio/transcriptions). Spends money from the account balance: most models are billed per second or minute of audio, some per token. usage.cost_rub is what this call cost.ConnectorAPI key
- Text-to-speech as base64 audio. Default: MeloTTS WAV, up to 2,000 chars, in English, Spanish, French, Chinese, Japanese or Korean, $0.002. quality "high": Deepgram Aura-2 natural English voices as MP3, up to 500 chars, $0.02. Price: $0.002 in USDC per successful call, paid with x402 (Base, Solana or Arc); failed calls are not charged.ConnectorNo auth
- Turns text into natural speech in English, Spanish, French, Chinese, Japanese or Korean in one or two seconds: Deepgram Aura-2 for English and Spanish, MeloTTS for the rest. Returns a hosted audio URL valid for 24 hours (MP3 for English and Spanish, WAV otherwise) plus its size; add inline=true to also get the base64. Up to 2000 characters per call. You are only charged if the audio is delivered. No API key, no account. $0.01 per call, paid over x402 (USDC).ConnectorNo auth
- Make a video: 1-30 images plus a narration script (spoken by a natural Deepgram Aura voice) or your own audio, with burned-in captions, rendered to MP4 in landscape, portrait (Reels/Shorts/TikTok) or square. $0.03 plus $0.09 per 1,000 narration characters. Costs $0.48 USDC per call (x402).ConnectorNo auth
- Live speech-to-text for voice agents (Deepgram Flux): get a WebSocket URL, stream raw 16-bit PCM audio, and receive live transcripts plus StartOfTurn / EndOfTurn events that tell your agent exactly when the caller has finished talking. $0.025 per minute (1-60 minutes). Costs $1.5 USDC per call (x402).ConnectorNo auth
- Premium transcription with Deepgram Nova-3: smart punctuation and formatting, language detection, optional speaker labels (diarization) and word timestamps, for a public audio or video file. $0.012 per audio minute plus $0.002 (set max_minutes), minimum $0.014. Add store=true (+$0.001) to get a 7-day share link instead of the data inline. Costs $1.443 USDC per call (x402).ConnectorNo auth
- Premium transcription with Deepgram Nova-3: smart punctuation and formatting, language detection, optional speaker labels (diarization) and word timestamps, for a public audio or video file. $0.012 per audio minute plus $0.002 (set max_minutes), minimum $0.014. Add store=true (+$0.001) to get a 7-day share link instead of the data inline. Costs $1.443 USDC per call (x402).ConnectorNo auth
- Premium natural speech with Deepgram Aura-2: 40 English voices (luna, orion, athena, zeus...) and Spanish, returned as MP3 (or base64 JSON). $0.002 plus $0.07 per 1,000 characters, minimum $0.005. Add store=true (+$0.001) to get a 7-day share link instead of the data inline. Costs $0.06 USDC per call (x402).ConnectorNo auth