Multi-provider routing
- Persona decides which model fits
- Calls this provider when its strengths apply
- Falls back to alternatives on rate-limits
8 tools available
Deepgram provides AI-powered speech recognition and understanding services, offering APIs for real-time and pre-recorded audio transcription, text-to-speech, and audio intelligence.
Connect Deepgram to Definable to route to the best model per task, mix providers in one workflow, fall back on rate-limits. Personas call Deepgram's 8 tools directly from chat or scheduled flows. Add it to your persona's available models and route requests to it where it fits best.
Every Deepgram action below is a callable tool any Definable persona can invoke.
Retrieve metadata for a specific Deepgram model by its UUID. Returns detailed model information including name, architecture, supported languages, version, and capabilities. Works for both STT (speech-to-text) and TTS (text-to-speech) models.
Retrieve metadata on all public Deepgram models (speech-to-text and text-to-speech). Returns comprehensive model information including supported languages, architectures, versions, and capabilities. Set include_outdated to True to include deprecated versions.
Tool to list all Deepgram projects. Use after authenticating with your API key.
Retrieves aggregated usage statistics for a Deepgram project including total audio duration, billable duration, number of requests, channels processed, and confidence/relevance scores. Returns both overall totals and breakdowns by model/accessor/tag. Use this to analyze API consumption, track costs, or monitor transcription quality metrics over time.
Tool to list all scopes for a specified Deepgram project. Use when you need to retrieve all permission scopes for a project.
Tool to list available think models for AI agent processing and voice agent configuration. Use when you need to see which think models are available for voice agents.
Tool to transcribe pre-recorded audio files into text. Use when converting a publicly accessible audio file URL to text. Primary transcript is at `results.channels[0].alternatives[0].transcript` in the response. Silent audio returns a valid empty transcript, not an error. Verify supported models and language codes via `DEEPGRAM_GET_MODELS` when uncertain.
Tool to convert text into natural-sounding speech. Use when you need TTS audio from text inputs.
Anything Deepgram exposes through its API. Common artificial intelligence workflows on Definable include route to the best model per task, mix providers in one workflow, fall back on rate-limits. Personas can call any of the 8 Deepgram tools directly, then chain the result into another integration without you writing code.
Deepgram uses API_KEY on Definable. You connect once from the integrations page, scoped to the permissions you choose, and from then on any persona that has the integration enabled can act on your behalf. Tokens are encrypted at rest and rotated automatically.
Yes — every Definable plan, including Starter, includes access to all 8 Deepgram tools. You only need a separate Deepgram subscription if Deepgram itself charges per seat or per API call.
Every call from a persona to Deepgram is logged with the user, persona, prompt, and response. Tokens never leave Definable's secrets vault, scopes are configurable per persona, and you can revoke access at any time from the integration page.
Sign up for Definable, open the integrations page, find Deepgram, and connect via OAuth or API key. You can immediately attach Deepgram to any persona and start running workflows. The free Starter plan includes 5,000 credits/month.
Definable exposes all 8 Deepgram actions as callable tools — including `Get Model by ID`, `Get Public Models`, `List Deepgram Projects`, plus 5 more. Each tool gets a typed parameter schema so personas know exactly how to call it.
Wire it up in minutes. No coding required.