{"id":"deepgram","name":"Deepgram","category":"media","summary":"Transcribe audio through hosted speech models.","description":"Use Deepgram’s API or CLI to turn recorded or streaming audio into text, with model-dependent language, formatting and speaker options. The CLI also exposes MCP access.","url":"https://aiagentstore.ai/services-for-ai-agents/deepgram","website":"https://deepgram.com?utm_source=aiagentstore.ai","docs":"https://developers.deepgram.com/developer-tools/cli/speech-to-text?utm_source=aiagentstore.ai","interfaces":["api","cli","mcp"],"capabilities":["speech-to-text","voice"],"humanSetup":"Create a Deepgram project, issue a scoped API key or sign in through the CLI, and choose an audio-processing budget and permitted input files.","authentication":"The CLI uses stored login credentials or DEEPGRAM_API_KEY. Its MCP server runs with dg mcp; inspect the connected tools because their schemas are supplied by the remote service.","billing":"Pay-as-you-go and committed plans charge according to the selected product and model. Speech recognition is priced by audio duration; optional processing features can add charges.","firstTask":"Transcribe a short authorized recording and compare the returned words, names and numbers with the original audio.","limitations":"Language support, concurrency and options vary by model and plan. CLI options do not forward arbitrary API parameters. A completed transcription can still contain errors.","readiness":"autonomous-after-setup","paymentMode":"provider-account","agentPayments":"not-verified","verifiedAt":"2026-10-16","verification":"Official documentation reviewed; account onboarding and paid execution not independently tested.","sources":["https://developers.deepgram.com/developer-tools/cli/speech-to-text?utm_source=aiagentstore.ai","https://developers.deepgram.com/developer-tools/cli/mcp-server?utm_source=aiagentstore.ai","https://deepgram.com/pricing?utm_source=aiagentstore.ai"],"siteGuide":{"title":"Keep the transcript traceable to the original audio","summary":"The dependency is trained speech-model inference and its serving capacity. Ordinary transcription orchestration code does not supply the acoustic model or compute service.","url":"https://aiagentstore.ai/services-for-ai-agents/deepgram#integration-playbook","contentType":"text/html","requiresBrowser":false,"includes":["selection rationale","suggested workflow","acceptance checks","failure recovery","related services"],"basis":"Original AI Agent Store editorial guidance; not an execution benchmark."},"categoryUrl":"https://aiagentstore.ai/services-for-ai-agents/category/media","tagLinks":[{"id":"api","url":"https://aiagentstore.ai/services-for-ai-agents/tag/api"},{"id":"cli","url":"https://aiagentstore.ai/services-for-ai-agents/tag/cli"},{"id":"mcp","url":"https://aiagentstore.ai/services-for-ai-agents/tag/mcp"},{"id":"speech-to-text","url":"https://aiagentstore.ai/services-for-ai-agents/tag/speech-to-text"},{"id":"voice","url":"https://aiagentstore.ai/services-for-ai-agents/tag/voice"}]}