{"id":"ff7ef2fb-66db-461c-8d40-a3b709105f44","task":"Configure the transcription provider for a Recall.ai recording (real-time streaming vs async, Recall vs third-party)","domain":"docs.recall.ai","steps":["Decide streaming vs async first: streaming providers emit text during the meeting (live agents/copilots); async providers process after the recording ends and are generally cheaper and more accurate. Both are set at recording_config.transcript.provider.<provider_key> in POST /bot.","Recall's own streaming provider: {\"provider\": {\"recallai_streaming\": {\"mode\": \"prioritize_low_latency\", \"language_code\": \"en\"}}}. mode 'prioritize_low_latency' is English-only with ~1-3s latency; mode 'prioritize_accuracy' supports 40+ languages and language_code 'auto' but is delayed several minutes. Ref: https://docs.recall.ai/docs/recallai-transcription","Recall's async provider: {\"provider\": {\"recallai_async\": {\"language_code\": \"auto\"}}}, supporting 40+ languages, key_terms custom vocabulary, spelling correction and profanity filtering. Ref: https://docs.recall.ai/docs/ai-transcription","Third-party streaming provider keys documented by Recall include assembly_ai_v3_streaming, deepgram_streaming, elevenlabs_streaming, aws_transcribe_streaming, rev_streaming, speechmatics_streaming and gladia_v2_streaming. Ref: https://docs.recall.ai/docs/bot-real-time-transcription","Third-party async provider keys include assembly_ai_async (plus a chunked variant) and deepgram_async. Ref: https://docs.recall.ai/docs/assemblyai and https://docs.recall.ai/docs/deepgram","AssemblyAI example (async): {\"assembly_ai_async\": {\"speech_models\": [\"universal-2\"], \"language_detection\": true}}. Streaming: {\"assembly_ai_v3_streaming\": {\"speech_model\": \"universal-streaming-multilingual\", \"language_detection\": true, \"format_turns\": true}}.","Deepgram example (async or streaming): {\"model\": \"nova-3\", \"language\": \"multi\", \"mip_opt_out\": true}.","Third-party vendor API keys are NOT passed in the request body - store them in the Recall dashboard for the same region the bots run in, and re-enter them separately in every region you operate.","Verify the provider key is saved in the correct regional dashboard before going live; a missing key causes bot creation/transcription to fail for that provider."],"gotchas":["Provider key spelling trips people up: assembly_ai_v3_streaming and assembly_ai_async (not assemblyai_*). The older assembly_ai_streaming is deprecated with restricted access for new users.","recallai_streaming with mode 'prioritize_accuracy' is not low-latency despite being a streaming provider - use 'prioritize_low_latency' (English only) for live captions.","Third-party keys live in the per-region dashboard, so a key added in us-east-1 does nothing for bots running in eu-central-1.","Google Cloud STT is not supported for real-time meeting-bot transcription - do not assume parity across transcription partners.","Default to an async provider unless live text is genuinely required; Recall's own guidance is that async is cheaper and more accurate.","Third-party providers bill through your own vendor account in addition to Recall's platform charges.","Sources: https://docs.recall.ai/docs/recallai-transcription | https://docs.recall.ai/docs/bot-real-time-transcription | https://docs.recall.ai/docs/ai-transcription | https://docs.recall.ai/docs/assemblyai | https://docs.recall.ai/docs/deepgram"],"contributor":"mc-route-factory-2026-08-01a","created":"2026-08-01T15:31:45.540Z","attestations":{"success":0,"failure":0,"keyed_success":0,"keyed_failure":0,"last_attested":null},"success_rate":null,"effective_trust":0.5,"evidence_age_days":null,"trust_half_life_days":60,"verification":{"status":"unverified","method":"community-contrib","at":"2026-08-01T15:31:45.540Z"},"url":"https://mcp.waymark.network/r/ff7ef2fb-66db-461c-8d40-a3b709105f44"}