{"category":{"id":"audio-speech","name":"Speech and audio","description":"Text-to-speech, speech-to-text, voice cloning, dubbing and audio intelligence."},"entries":[
{"id":"amazon-polly-amazon-transcribe-aws","name":"Amazon Polly / Amazon Transcribe (AWS)","homepage":"https://aws.amazon.com/polly/","docs":"https://docs.aws.amazon.com/polly/latest/dg/what-is.html","auth":"cloud_iam","auth_hint":"AWS SigV4 signing with IAM access keys","mcp":{"type":"official","url":"https://github.com/awslabs/mcp/tree/main/src/aws-api-mcp-server","maintainer":"vendor","repo":"https://github.com/awslabs/mcp/tree/main/src/aws-api-mcp-server","tools":["call_aws","suggest_aws_commands","get_execution_plan"],"covers_full_api":true,"source_url":"https://github.com/awslabs/mcp/tree/main/src/aws-api-mcp-server","checked_at":"2026-09-24","domain_verified":null,"kind":"official","config":null},"free_tier":"Free tier: Polly 5M chars/mo standard (neural 1M, generative 100K chars/mo for first 12 months), Transcribe 60 min/mo (12 months); new AWS accounts since 2025-07-15 get up to $200 Free Tier credits","sdk":["python","javascript","java","go","dotnet"],"openapi":null,"llms_txt":null,"desc_en":"Convert text to lifelike speech (Polly) and transcribe audio with speaker diarization (Transcribe) via AWS API.","notes":"Needs an AWS account and IAM credentials. Voice and feature availability differs by region. Transcribe docs: https://docs.aws.amazon.com/transcribe/latest/dg/what-is.html. The generic AWS API MCP Server (awslabs) runs AWS CLI commands, incl. polly and transcribe.","verified":"2026-09-24","free_plan":{"kind":"free_tier","requires_card":true,"quota":"Polly: 5M standard chars/month (neural 1M for first 12 months); Transcribe: 60 min/month for 12 months","period":"month","source_url":"https://aws.amazon.com/polly/pricing/","checked_at":"2026-09-24"},"auth_scheme":{"type":"cloud_iam","format":"AWS Signature Version 4 (Authorization: AWS4-HMAC-SHA256 ...) signed with IAM credentials","source_url":"https://docs.aws.amazon.com/general/latest/gr/pol.html","checked_at":"2026-09-24"},"base_url":"https://polly.<region>.amazonaws.com","async_jobs":{"value":true,"how":"Transcribe: StartTranscriptionJob, then poll GetTranscriptionJob","source_url":"https://aws.amazon.com/transcribe/faqs/"},"data_policy":{"summary":"Transcribe may store and use voice inputs to improve AWS AI services; opt out via AWS Organizations AI services opt-out policy","source_url":"https://aws.amazon.com/transcribe/faqs/","checked_at":"2026-09-24"},"operations":["text-to-speech","speech-to-text"],"no_auth":false,"call":{"operation":"synthesize speech from text (Polly)","method":"POST","url":"https://polly.{region}.amazonaws.com/v1/speech","example":"curl -X POST https://polly.us-east-1.amazonaws.com/v1/speech --aws-sigv4 \"aws:amz:us-east-1:polly\" --user \"$AWS_ACCESS_KEY_ID:$AWS_SECRET_ACCESS_KEY\" -H \"Content-Type: application/json\" -d '{\"Text\":\"Hello from Polly\",\"OutputFormat\":\"mp3\",\"VoiceId\":\"Joanna\",\"Engine\":\"neural\"}' -o speech.mp3","response_fields":["body: audio stream","Content-Type header","x-amzn-RequestCharacters header"],"async":null,"source_url":"https://docs.aws.amazon.com/polly/latest/dg/API_SynthesizeSpeech.html","checked_at":"2026-09-24"},"unit_price":{"summary":"Polly: standard $4.00, neural $16.00, generative $30.00, long-form $100.00 per 1M characters (beyond free tier)","source_url":"https://aws.amazon.com/polly/pricing/","checked_at":"2026-09-24"},"has_free_tier":true,"has_trial":false,"no_card":false,"stale":false,"link_check":{"checked_at":"2026-09-24","docs":"ok"}},
{"id":"assemblyai-api","name":"AssemblyAI API","homepage":"https://www.assemblyai.com","docs":"https://www.assemblyai.com/docs","auth":"api_key","auth_hint":"Authorization: <key> (no Bearer prefix)","mcp":{"type":"none","url":null,"maintainer":"none","source_url":"https://www.assemblyai.com/docs/coding-agent-prompts","checked_at":"2026-09-24","domain_verified":null,"kind":"none","config":null},"free_tier":"Trial: $50 in free credits one-time on signup, no card required, credits do not expire (LLM Gateway not included); then pay-as-you-go","sdk":["python","typescript"],"openapi":"https://www.assemblyai.com/docs/openapi.json","llms_txt":"https://www.assemblyai.com/docs/llms.txt","desc_en":"Transcribe recorded or streaming audio with speaker diarization, sentiment analysis and LLM-based audio insights via REST.","notes":"Vendor MCP at https://assemblyai.com/docs/mcp only searches the docs. To run transcriptions, call the REST API or an SDK.","verified":"2026-09-24","free_plan":{"kind":"trial","requires_card":false,"quota":"$50 credits (do not expire)","period":"one_time","source_url":"https://www.assemblyai.com/docs/billing-and-pricing","checked_at":"2026-09-24"},"auth_scheme":{"type":"apiKey","in":"header","name":"authorization","format":"authorization: <ASSEMBLYAI_API_KEY>","source_url":"https://www.assemblyai.com/docs/pre-recorded-audio/api-reference/transcripts/submit","checked_at":"2026-09-24"},"base_url":"https://api.assemblyai.com","rate_limits":{"summary":"Pre-recorded: 5 parallel transcriptions on free accounts, 200+ on paid; excess jobs are queued FIFO","source_url":"https://www.assemblyai.com/docs/pre-recorded-audio/rate-limits","checked_at":"2026-09-24"},"async_jobs":{"value":true,"how":"POST /v2/transcript returns id; poll GET /v2/transcript/{id} or set webhook_url","source_url":"https://www.assemblyai.com/docs/pre-recorded-audio/api-reference/transcripts/submit"},"data_policy":{"summary":"Certain API files may be used for model training after redaction unless opted out; zero data retention for Streaming when opted out","source_url":"https://www.assemblyai.com/docs/data-retention-and-model-training","checked_at":"2026-09-24"},"operations":["speech-to-text"],"no_auth":false,"call":{"operation":"transcribe an audio file","method":"POST","url":"https://api.assemblyai.com/v2/transcript","example":"curl -X POST https://api.assemblyai.com/v2/transcript -H \"authorization: $ASSEMBLYAI_API_KEY\" -H \"content-type: application/json\" -d '{\"audio_url\": \"https://assembly.ai/wildfires.mp3\"}'","response_fields":["id","status","text","confidence"],"async":"poll GET https://api.assemblyai.com/v2/transcript/{id} until status is completed or error","source_url":"https://www.assemblyai.com/docs/api-reference/transcripts/submit","checked_at":"2026-09-24"},"unit_price":{"summary":"Pre-recorded speech-to-text: Universal-3.5 Pro $0.21 per audio hour, Universal-2 $0.15 per hour","source_url":"https://www.assemblyai.com/pricing","checked_at":"2026-09-24"},"has_free_tier":false,"has_trial":true,"no_card":true,"stale":false,"link_check":{"checked_at":"2026-09-24","docs":"ok","mcp":"reachable","openapi":"ok","llms_txt":"ok"},"uptime":{"window_days":30,"api":{"url":"https://api.assemblyai.com","probes":1,"up":1,"median_ms":402,"last":{"at":"2026-09-24T18:26Z","up":true,"detail":404}},"mcp_remote":{"url":"https://assemblyai.com/docs/mcp","probes":1,"up":1,"median_ms":282,"last":{"at":"2026-09-24T18:26Z","up":true,"detail":308}}}},
{"id":"azure-ai-speech","name":"Azure AI Speech","homepage":"https://azure.microsoft.com/products/ai-services/ai-speech","docs":"https://learn.microsoft.com/azure/ai-services/speech-service/","auth":"cloud_iam","auth_hint":"Ocp-Apim-Subscription-Key: <key>, or Authorization: Bearer <Entra token>","mcp":{"type":"official","url":"https://github.com/microsoft/mcp","maintainer":"vendor","repo":"https://github.com/microsoft/mcp","tools":["speech stt recognize","speech tts synthesize"],"covers_full_api":false,"source_url":"https://learn.microsoft.com/en-us/azure/developer/azure-mcp-server/tools/ai-services-speech","checked_at":"2026-09-24","domain_verified":null,"kind":"official","config":{"transport":"stdio","command":"npx","args":["-y","@azure/mcp@latest","server","start"],"env":["AZURE_TENANT_ID","AZURE_CLIENT_ID","AZURE_CLIENT_SECRET"],"docs_only":false,"source_url":"https://github.com/microsoft/mcp/blob/main/servers/Azure.Mcp.Server/README.md","checked_at":"2026-09-24"}},"free_tier":"Free tier (F0): 5 audio hrs/mo STT, 0.5M chars/mo neural TTS; batch transcription not available on F0","sdk":["python","csharp","cpp","java","javascript","go","objective-c"],"openapi":null,"llms_txt":null,"desc_en":"Convert text to speech, transcribe speech to text and translate speech via REST or Speech SDK.","notes":"Now branded 'Azure Speech in Foundry Tools'. Needs an Azure Speech resource, and endpoints are per region. Speech tools (speech stt recognize, speech tts synthesize) ship in the Azure MCP Server.","verified":"2026-09-24","free_plan":{"kind":"free_tier","quota":"5 audio hours STT + 0.5M neural TTS characters","period":"month","source_url":"https://azure.microsoft.com/en-us/pricing/details/cognitive-services/speech-services/","checked_at":"2026-09-24"},"auth_scheme":{"type":"apiKey","in":"header","name":"Ocp-Apim-Subscription-Key","format":"Ocp-Apim-Subscription-Key: <RESOURCE_KEY> (or Authorization: Bearer <token>)","source_url":"https://learn.microsoft.com/en-us/azure/ai-services/speech-service/rest-speech-to-text-short","checked_at":"2026-09-24"},"rate_limits":{"summary":"F0 quotas are not adjustable; F0 TTS 20 transactions per 60 seconds","source_url":"https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-services-quotas-and-limits","checked_at":"2026-09-24"},"operations":["text-to-speech","speech-to-text"],"no_auth":false,"call":{"operation":"convert text to speech","method":"POST","url":"https://{region}.tts.speech.microsoft.com/cognitiveservices/v1","example":"curl -X POST \"https://$SPEECH_REGION.tts.speech.microsoft.com/cognitiveservices/v1\" -H \"Ocp-Apim-Subscription-Key: $SPEECH_KEY\" -H \"Content-Type: application/ssml+xml\" -H \"X-Microsoft-OutputFormat: audio-16khz-128kbitrate-mono-mp3\" -H \"User-Agent: curl\" --data-raw \"<speak version='1.0' xml:lang='en-US'><voice xml:lang='en-US' xml:gender='Female' name='en-US-Ava:DragonHDLatestNeural'>Hello from Azure Speech</voice></speak>\" --output output.mp3","response_fields":["binary audio body in the X-Microsoft-OutputFormat format (HTTP 200)"],"async":null,"source_url":"https://learn.microsoft.com/en-us/azure/ai-services/speech-service/get-started-text-to-speech?pivots=programming-language-rest","checked_at":"2026-09-24"},"unit_price":{"summary":"Pay-as-you-go (East US, S1): neural text to speech $15 per 1M characters; real-time speech to text $1 per audio hour","source_url":"https://prices.azure.com/api/retail/prices?$filter=productName eq 'Azure Speech' and armRegionName eq 'eastus'","checked_at":"2026-09-24"},"has_free_tier":true,"has_trial":false,"no_card":false,"stale":false,"link_check":{"checked_at":"2026-09-24","docs":"ok","mcp":"ok"},"ratings":[{"source":"github","repo":"microsoft/azure-speech-mcp-server","stars":1,"forks":1,"pushed_at":"2025-11-24","archived":false,"url":"https://github.com/microsoft/azure-speech-mcp-server","fetched_at":"2026-09-24T16:54Z"}]},
{"id":"cartesia-api","name":"Cartesia API","homepage":"https://cartesia.ai","docs":"https://docs.cartesia.ai","auth":"api_key","auth_hint":"Authorization: Bearer <key> plus Cartesia-Version header","mcp":{"type":"official","url":"https://mcp.cartesia.ai/mcp","maintainer":"vendor","remote_url":"https://mcp.cartesia.ai/mcp","tools":["text_to_speech","speech_to_text","list_voices","get_voice","clone_voice","update_voice","delete_voice","voice_change","localize_voice","list_pronunciation_dicts","create_pronunciation_dict","get_pronunciation_dict","update_pronunciation_dict","delete_pronunciation_dict","download_file","get_credit_usage"],"covers_full_api":false,"source_url":"https://docs.cartesia.ai/tools/ai/mcp.md","checked_at":"2026-09-24","domain_verified":true,"kind":"vendor-hosted","config":{"transport":"streamable-http","url":"https://mcp.cartesia.ai/mcp","headers":null,"oauth":true,"env":[],"docs_only":false,"source_url":"https://docs.cartesia.ai/tools/ai/mcp.md","checked_at":"2026-09-24"}},"free_tier":"Free tier: 20,000 credits/mo; no commercial-use license and no voice cloning","sdk":["python","typescript","go"],"openapi":null,"llms_txt":"https://docs.cartesia.ai/llms.txt","desc_en":"Generate low-latency real-time text-to-speech, transcribe speech and clone voices via REST/WebSocket API.","notes":"The hosted MCP endpoint uses OAuth. The local MCP server is at https://github.com/cartesia-ai/cartesia-mcp.","verified":"2026-09-24","free_plan":{"kind":"free_tier","quota":"20K credits (~1 credit per TTS character)","period":"month","source_url":"https://cartesia.ai/pricing","checked_at":"2026-09-24"},"auth_scheme":{"type":"http","scheme":"bearer","format":"Authorization: Bearer <API_KEY> + Cartesia-Version: 2026-08-14 (X-Api-Key also accepted)","source_url":"https://docs.cartesia.ai/get-started/authenticate-your-client-applications.md","checked_at":"2026-09-24"},"base_url":"https://api.cartesia.ai","rate_limits":{"summary":"Free plan: 2 concurrent TTS requests, 8 concurrent STT requests; limits scale with subscription plan","source_url":"https://cartesia.ai/pricing","checked_at":"2026-09-24"},"data_policy":{"summary":"Zero Data Retention available to Enterprise customers for TTS and STT","source_url":"https://docs.cartesia.ai/enterprise/zero-data-retention.md","checked_at":"2026-09-24"},"operations":["text-to-speech","speech-to-text","voice-cloning"],"no_auth":false,"call":{"operation":"text-to-speech (audio file)","method":"POST","url":"https://api.cartesia.ai/tts/bytes","example":"curl -X POST https://api.cartesia.ai/tts/bytes -H \"Cartesia-Version: 2026-08-14\" -H \"Authorization: Bearer $CARTESIA_API_KEY\" -H \"Content-Type: application/json\" -d '{\"model_id\":\"sonic-3.6\",\"transcript\":\"Hi there, nice to meet you.\",\"voice\":\"db6b0ed5-d5d3-463d-ae85-518a07d3c2b4\",\"output_format\":{\"container\":\"wav\",\"encoding\":\"pcm_s16le\",\"sample_rate\":44100}}' -o out.wav","response_fields":["body (audio bytes in output_format)"],"async":null,"source_url":"https://docs.cartesia.ai/api-reference/tts/bytes","checked_at":"2026-09-24"},"unit_price":{"summary":"TTS: about 1 credit per character; Pro plan $5/mo for 100K credits, Startup $49/mo for 1.25M credits","source_url":"https://docs.cartesia.ai/pricing","checked_at":"2026-09-24"},"has_free_tier":true,"has_trial":false,"no_card":false,"stale":false,"link_check":{"checked_at":"2026-09-24","docs":"ok","mcp":"reachable","llms_txt":"ok"},"uptime":{"window_days":30,"api":{"url":"https://api.cartesia.ai","probes":1,"up":1,"median_ms":694,"last":{"at":"2026-09-24T18:26Z","up":true,"detail":200}},"mcp_remote":{"url":"https://mcp.cartesia.ai/mcp","probes":1,"up":1,"median_ms":569,"last":{"at":"2026-09-24T18:26Z","up":true,"detail":401}}}},
{"id":"deepgram-api","name":"Deepgram API","homepage":"https://deepgram.com","docs":"https://developers.deepgram.com/reference/deepgram-api-overview","auth":"api_key","auth_hint":"Authorization: Token <key>","mcp":{"type":"official","url":"https://github.com/deepgram/mcp","maintainer":"vendor","repo":"https://github.com/deepgram/mcp","source_url":"https://github.com/deepgram/mcp","checked_at":"2026-09-24","domain_verified":null,"kind":"official","config":{"transport":"streamable-http","url":"https://developers.deepgram.com/_mcp/server","headers":null,"oauth":false,"env":[],"docs_only":true,"source_url":"https://developers.deepgram.com/developer-tools/cli/mcp-server.md","checked_at":"2026-09-24"}},"free_tier":"Trial: $200 in free credit one-time on signup, no credit card required; then pay-as-you-go","sdk":["python","typescript","go","rust","dotnet"],"openapi":"https://developers.deepgram.com/openapi.yaml","llms_txt":"https://developers.deepgram.com/llms.txt","desc_en":"Transcribe batch or streaming audio with diarization, synthesize speech, and run real-time voice agents via REST/WebSocket.","notes":"Hosted MCP at https://developers.deepgram.com/_mcp/server only searches the docs; the API-calling server is local `dg mcp` (Deepgram CLI) or pip deepgram-mcp.","verified":"2026-09-24","free_plan":{"kind":"trial","requires_card":false,"quota":"$200 credit","period":"one_time","source_url":"https://deepgram.com/pricing","checked_at":"2026-09-24"},"auth_scheme":{"type":"apiKey","in":"header","name":"Authorization","format":"Authorization: Token <DEEPGRAM_API_KEY>","source_url":"https://developers.deepgram.com/reference/authentication.md","checked_at":"2026-09-24"},"base_url":"https://api.deepgram.com","rate_limits":{"summary":"Nova-3/Nova-2: up to 50 concurrent pre-recorded and 150 streaming requests; Voice Agent API up to 45 concurrent connections","source_url":"https://developers.deepgram.com/reference/api-rate-limits.md","checked_at":"2026-09-24"},"data_policy":{"summary":"Model Improvement Program may use data for training; opt out per request with mip_opt_out=true","source_url":"https://developers.deepgram.com/docs/the-deepgram-model-improvement-partnership-program.md","checked_at":"2026-09-24"},"operations":["speech-to-text","text-to-speech","voice-agent"],"no_auth":false,"call":{"operation":"transcribe a pre-recorded audio file from a URL","method":"POST","url":"https://api.deepgram.com/v1/listen","example":"curl -X POST 'https://api.deepgram.com/v1/listen?model=nova-3' -H \"Authorization: Token $DEEPGRAM_API_KEY\" -H 'Content-Type: application/json' -d '{\"url\": \"https://dpgr.am/spacewalk.wav\"}'","response_fields":["results.channels[0].alternatives[0].transcript","results.channels[0].alternatives[0].confidence","metadata.request_id","metadata.duration"],"async":null,"source_url":"https://developers.deepgram.com/reference/speech-to-text/listen-pre-recorded","checked_at":"2026-09-24"},"unit_price":{"summary":"Nova-3 monolingual pre-recorded transcription: $0.0043 per audio minute (pay-as-you-go)","source_url":"https://deepgram.com/pricing","checked_at":"2026-09-24"},"has_free_tier":false,"has_trial":true,"no_card":true,"stale":false,"link_check":{"checked_at":"2026-09-24","docs":"ok","mcp":"ok","openapi":"ok","llms_txt":"ok"},"ratings":[{"source":"github","repo":"deepgram/mcp","stars":2,"forks":2,"pushed_at":"2026-05-06","archived":false,"url":"https://github.com/deepgram/mcp","fetched_at":"2026-09-24T16:54Z"}],"uptime":{"window_days":30,"api":{"url":"https://api.deepgram.com","probes":1,"up":1,"median_ms":402,"last":{"at":"2026-09-24T18:26Z","up":true,"detail":404}},"mcp_remote":{"url":"https://developers.deepgram.com/_mcp/server","probes":1,"up":1,"median_ms":414,"last":{"at":"2026-09-24T18:26Z","up":true,"detail":200}}}},
{"id":"elevenlabs-api","name":"ElevenLabs API","homepage":"https://elevenlabs.io","docs":"https://elevenlabs.io/docs/api-reference/introduction","auth":"api_key","auth_hint":"xi-api-key: <key>","mcp":{"type":"official","url":"https://api.elevenlabs.io/v1/mcp","maintainer":"vendor","remote_url":"https://api.elevenlabs.io/v1/mcp","repo":"https://github.com/elevenlabs/elevenlabs-mcp","source_url":"https://github.com/elevenlabs/elevenlabs-mcp","checked_at":"2026-09-24","domain_verified":true,"kind":"vendor-hosted","config":null,"issue":"repo archived 2026-08-20; replaced by hosted OAuth server https://api.elevenlabs.io/v1/mcp"},"free_tier":"Free: limited monthly credits; non-commercial use with attribution only, no voice cloning","sdk":["python","typescript","swift","kotlin","flutter"],"openapi":"https://api.elevenlabs.io/openapi.json","llms_txt":"https://elevenlabs.io/docs/llms.txt","desc_en":"Generate, clone and stream text-to-speech voices and transcribe audio via REST/WebSocket API.","notes":"Official hosted MCP https://api.elevenlabs.io/v1/mcp uses OAuth; the local stdio repo elevenlabs/elevenlabs-mcp is archived since 2026-08-20.","verified":"2026-09-24","operations":["text-to-speech","voice-cloning","speech-to-text"],"free_plan":{"kind":"free_tier","period":"month","source_url":"https://elevenlabs.io/docs/overview/administration/billing.md","checked_at":"2026-09-24"},"auth_scheme":{"type":"apiKey","in":"header","name":"xi-api-key","format":"xi-api-key: <ELEVENLABS_API_KEY>","source_url":"https://elevenlabs.io/docs/api-reference/authentication.md","checked_at":"2026-09-24"},"base_url":"https://api.elevenlabs.io/v1","rate_limits":{"summary":"Free plan concurrency: 2 (Multilingual v2), 4 (Flash), 8 STT, 6 realtime STT; excess requests are queued","source_url":"https://elevenlabs.io/docs/overview/models.md","checked_at":"2026-09-24"},"no_auth":false,"call":{"operation":"convert text to speech","method":"POST","url":"https://api.elevenlabs.io/v1/text-to-speech/{voice_id}","example":"curl -X POST https://api.elevenlabs.io/v1/text-to-speech/$VOICE_ID -H \"xi-api-key: $ELEVENLABS_API_KEY\" -H \"Content-Type: application/json\" -d '{\"text\":\"Hello\",\"model_id\":\"eleven_multilingual_v2\"}' --output out.mp3","response_fields":["body: binary audio (default mp3_44100_128)","header character-cost","header request-id"],"async":null,"source_url":"https://elevenlabs.io/docs/api-reference/text-to-speech/convert","checked_at":"2026-09-24"},"unit_price":{"summary":"TTS API pay-as-you-go: $0.10 per 1,000 characters (Multilingual v2 / v3), $0.05 per 1,000 (Flash / Turbo)","source_url":"https://elevenlabs.io/pricing/api","checked_at":"2026-09-24"},"has_free_tier":true,"has_trial":false,"no_card":false,"stale":false,"link_check":{"checked_at":"2026-09-24","docs":"ok","mcp":"ok","openapi":"ok","llms_txt":"ok"},"ratings":[{"source":"github","repo":"elevenlabs/elevenlabs-mcp","stars":1537,"forks":256,"pushed_at":"2026-08-20","archived":true,"url":"https://github.com/elevenlabs/elevenlabs-mcp","fetched_at":"2026-09-24T16:54Z"},{"source":"sourceforge","rating":4.0,"reviews":4,"url":"https://sourceforge.net/software/product/ElevenLabs/","fetched_at":"2026-09-24T16:56Z"}],"uptime":{"window_days":30,"api":{"url":"https://api.elevenlabs.io/v1","probes":1,"up":1,"median_ms":340,"last":{"at":"2026-09-24T18:26Z","up":true,"detail":404}},"mcp_remote":{"url":"https://api.elevenlabs.io/v1/mcp","probes":1,"up":1,"median_ms":310,"last":{"at":"2026-09-24T18:26Z","up":true,"detail":401}}},"reviews_url":"https://raw.githubusercontent.com/eater2/ai_agents_api_library/main/catalog/reviews/elevenlabs-api.json"},
{"id":"google-cloud-text-to-speech-speech-to-text","name":"Google Cloud Text-to-Speech / Speech-to-Text","homepage":"https://cloud.google.com/text-to-speech","docs":"https://cloud.google.com/text-to-speech/docs","auth":"cloud_iam","auth_hint":"API key (?key=) or OAuth2 service-account token: Authorization: Bearer <token>","mcp":{"type":"official","url":"https://github.com/GoogleCloudPlatform/genmedia-creative-studio/tree/main/experiments/mcp-genmedia","maintainer":"vendor","repo":"https://github.com/GoogleCloudPlatform/genmedia-creative-studio/tree/main/experiments/mcp-genmedia","tools":["chirp_tts","list_chirp_voices"],"covers_full_api":false,"source_url":"https://github.com/GoogleCloudPlatform/genmedia-creative-studio/blob/main/experiments/mcp-genmedia/mcp-genmedia-go/README.md","checked_at":"2026-09-24","domain_verified":null,"kind":"official","config":null},"free_tier":"Free tier: TTS 4M chars/mo Standard and WaveNet, 1M chars/mo Neural2, Chirp 3 HD and Studio; STT 60 min/mo","sdk":["python","nodejs","go","java","php","ruby","csharp"],"openapi":"https://texttospeech.googleapis.com/$discovery/rest?version=v1","llms_txt":null,"desc_en":"Synthesize lifelike speech from text and transcribe audio to text via REST/gRPC using GCP credentials.","notes":"Requires a GCP project with billing enabled. Speech-to-Text docs are separate: https://cloud.google.com/speech-to-text/docs. Experimental vendor MCP mcp-chirp3-go (Genmedia) covers Chirp 3 HD TTS only.","verified":"2026-09-24","operations":["text-to-speech","speech-to-text"],"free_plan":{"kind":"free_tier","quota":"TTS: 4M chars Standard/WaveNet, 1M Neural2/Chirp 3 HD/Studio; STT: 60 min","period":"month","source_url":"https://cloud.google.com/text-to-speech/pricing","checked_at":"2026-09-24"},"auth_scheme":{"type":"cloud_iam","scheme":"bearer","format":"Authorization: Bearer $(gcloud auth print-access-token) + x-goog-user-project: <PROJECT_ID>","source_url":"https://cloud.google.com/text-to-speech/docs/create-audio-text-command-line","checked_at":"2026-09-24"},"base_url":"https://texttospeech.googleapis.com/v1","data_policy":{"summary":"STT offers a cheaper 'with data logging' price tier (opt-in); 'without data logging' tier costs more","source_url":"https://cloud.google.com/speech-to-text/pricing","checked_at":"2026-09-24"},"no_auth":false,"call":{"operation":"synthesize speech from text","method":"POST","url":"https://texttospeech.googleapis.com/v1/text:synthesize","example":"curl -X POST https://texttospeech.googleapis.com/v1/text:synthesize -H \"Authorization: Bearer $(gcloud auth print-access-token)\" -H \"x-goog-user-project: $GCP_PROJECT_ID\" -H \"Content-Type: application/json; charset=utf-8\" -d '{\"input\":{\"text\":\"Hello world\"},\"voice\":{\"languageCode\":\"en-gb\",\"name\":\"en-GB-Standard-A\"},\"audioConfig\":{\"audioEncoding\":\"MP3\"}}'","response_fields":["audioContent"],"async":null,"source_url":"https://docs.cloud.google.com/text-to-speech/docs/create-audio-text-command-line","checked_at":"2026-09-24"},"unit_price":{"summary":"TTS after free tier: Standard and WaveNet $4, Neural2 $16, Chirp 3 HD $30, Studio $160 per 1M characters","source_url":"https://docs.cloud.google.com/text-to-speech/pricing","checked_at":"2026-09-24"},"has_free_tier":true,"has_trial":false,"no_card":false,"stale":false,"link_check":{"checked_at":"2026-09-24","docs":"ok","openapi":"ok"},"uptime":{"window_days":30,"api":{"url":"https://texttospeech.googleapis.com/v1","probes":1,"up":1,"median_ms":246,"last":{"at":"2026-09-24T18:26Z","up":true,"detail":404}}}},
{"id":"hume-ai-api","name":"Hume AI API","homepage":"https://www.hume.ai","docs":"https://dev.hume.ai/docs","auth":"api_key","auth_hint":"X-Hume-Api-Key: <key> (REST); api_key query param (EVI WebSocket)","mcp":{"type":"official","url":"https://github.com/HumeAI/mcp-server-hume","maintainer":"vendor","repo":"https://github.com/HumeAI/mcp-server-hume","tools":["tts","play_previous_audio","list_voices","save_voice","delete_voice"],"covers_full_api":false,"source_url":"https://dev.hume.ai/docs/integrations/mcp.md","checked_at":"2026-09-24","domain_verified":null,"kind":"official","config":{"transport":"streamable-http","url":"https://dev.hume.ai/_mcp/server","headers":null,"oauth":false,"env":[],"docs_only":true,"source_url":"https://dev.hume.ai/docs/integrations/mcp.md","checked_at":"2026-09-24"}},"free_tier":"Free tier: 10,000 TTS chars/mo + 5 EVI min/mo; new accounts also get $20 in credits","sdk":["python","typescript"],"openapi":null,"llms_txt":null,"desc_en":"Generate expressive text-to-speech and run real-time empathic voice conversations (EVI) via REST/WebSocket.","notes":"The free plan allows 1 concurrent connection. Voice cloning is on paid plans. The API MCP is local `npx @humeai/mcp-server` (HUME_API_KEY); dev.hume.ai/_mcp/server only searches the docs.","verified":"2026-09-24","operations":["text-to-speech","voice-agent"],"free_plan":{"kind":"free_tier","quota":"10,000 TTS characters (~10 min); new accounts also get $20 credits","period":"month","source_url":"https://www.hume.ai/pricing","checked_at":"2026-09-24"},"auth_scheme":{"type":"apiKey","in":"header","name":"X-Hume-Api-Key","format":"X-Hume-Api-Key: <HUME_API_KEY>","source_url":"https://dev.hume.ai/docs/introduction/api-key.md","checked_at":"2026-09-24"},"base_url":"https://api.hume.ai/v0","rate_limits":{"summary":"Free plan TTS: 15 requests per minute","source_url":"https://www.hume.ai/pricing","checked_at":"2026-09-24"},"data_policy":{"summary":"By default anonymized EVI interaction data is used for training; users can opt out and enable 'Do not retain data'","source_url":"https://dev.hume.ai/docs/resources/privacy.md","checked_at":"2026-09-24"},"no_auth":false,"call":{"operation":"text-to-speech","method":"POST","url":"https://api.hume.ai/v0/tts","example":"curl -X POST https://api.hume.ai/v0/tts -H \"X-Hume-Api-Key: $HUME_API_KEY\" -H \"Content-Type: application/json\" -d '{\"utterances\": [{\"text\": \"Hello from Hume.\", \"description\": \"a calm, friendly narrator\"}], \"format\": {\"type\": \"mp3\"}}'","response_fields":["generations[0].audio","generations[0].duration","generations[0].generation_id","request_id"],"async":null,"source_url":"https://dev.hume.ai/reference/text-to-speech-tts/synthesize-json","checked_at":"2026-09-24"},"unit_price":{"summary":"TTS overage per 1,000 characters: $0.15 (Creator), $0.12 (Pro), $0.10 (Scale), $0.05 (Business); EVI $0.04-0.07/minute","source_url":"https://www.hume.ai/pricing","checked_at":"2026-09-24"},"has_free_tier":true,"has_trial":false,"no_card":false,"stale":false,"link_check":{"checked_at":"2026-09-24","docs":"ok","mcp":"ok"},"uptime":{"window_days":30,"api":{"url":"https://api.hume.ai/v0","probes":1,"up":1,"median_ms":502,"last":{"at":"2026-09-24T18:26Z","up":true,"detail":404}}}},
{"id":"murf-ai-api","name":"Murf AI API","homepage":"https://murf.ai","docs":"https://murf.ai/api/docs/introduction/overview","auth":"api_key","auth_hint":"api-key: <key> request header (base URL https://api.murf.ai/v1)","mcp":{"type":"official","url":"https://github.com/murf-ai/murf-mcp","maintainer":"vendor","repo":"https://github.com/murf-ai/murf-mcp","covers_full_api":false,"source_url":"https://murf.ai/api/docs/integrations/mcp-server.md","checked_at":"2026-09-24","domain_verified":null,"kind":"official","config":null},"free_tier":"Trial: 100,000 characters one-time on the free API plan, no time limit","sdk":["python"],"openapi":null,"llms_txt":null,"desc_en":"Generate AI voiceovers, clone voices and dub audio in 35+ languages via REST API.","notes":"Two model families: Falcon 2 (low latency, for streaming; $0.01/min) and Gen2 (studio quality).","verified":"2026-09-24","operations":["text-to-speech","voice-cloning"],"free_plan":{"kind":"trial","quota":"100,000 characters (no time limit)","period":"one_time","source_url":"https://murf.ai/api/docs/resources/faq.md","checked_at":"2026-09-24"},"auth_scheme":{"type":"apiKey","in":"header","name":"api-key","format":"api-key: <MURF_API_KEY>","source_url":"https://murf.ai/api/docs/api-reference/text-to-speech/generate.md","checked_at":"2026-09-24"},"base_url":"https://api.murf.ai/v1","rate_limits":{"summary":"Free tier streaming concurrency: Falcon 2 5 (US-East) or 2 (global/regional), Gen2 5; WebSocket connections 10x concurrency","source_url":"https://murf.ai/api/docs/resources/rate-limits.md","checked_at":"2026-09-24"},"no_auth":false,"call":{"operation":"text-to-speech (generate a voiceover file)","method":"POST","url":"https://api.murf.ai/v1/speech/generate","example":"curl -X POST https://api.murf.ai/v1/speech/generate -H \"api-key: $MURF_API_KEY\" -H 'Content-Type: application/json' -d '{\"text\": \"Hi, how are you doing today?\", \"voiceId\": \"en-US-natalie\"}'","response_fields":["audioFile","audioLengthInSeconds","remainingCharacterCount","wordDurations"],"async":null,"source_url":"https://murf.ai/api/docs/api-reference/text-to-speech/generate","checked_at":"2026-09-24"},"unit_price":{"summary":"Pay-as-you-go: $0.03 per 1,000 characters (minimum purchase $2); Falcon streaming model advertised at $0.01 per minute of speech","source_url":"https://help.murf.ai/murf-api-plans-and-limits","checked_at":"2026-09-24"},"has_free_tier":false,"has_trial":true,"no_card":false,"stale":false,"link_check":{"checked_at":"2026-09-24","docs":"ok"},"ratings":[{"source":"sourceforge","rating":5.0,"reviews":7,"url":"https://sourceforge.net/software/product/Murf-AI/","fetched_at":"2026-09-24T16:56Z"}],"uptime":{"window_days":30,"api":{"url":"https://api.murf.ai/v1","probes":1,"up":1,"median_ms":481,"last":{"at":"2026-09-24T18:26Z","up":true,"detail":404}}},"reviews_url":"https://raw.githubusercontent.com/eater2/ai_agents_api_library/main/catalog/reviews/murf-ai-api.json"},
{"id":"openai-audio-api-tts-transcription","name":"OpenAI Audio API (TTS / transcription)","homepage":"https://platform.openai.com/docs/guides/audio","docs":"https://developers.openai.com/api/docs/guides/text-to-speech","auth":"api_key","auth_hint":"Authorization: Bearer <key>","mcp":{"type":"none","url":null,"domain_verified":null,"kind":"none","config":null},"free_tier":"paid only (pay-per-use)","sdk":["python","typescript","go","java","dotnet"],"openapi":"https://github.com/openai/openai-openapi","llms_txt":"https://developers.openai.com/llms.txt","desc_en":"Synthesize speech with TTS models and transcribe or translate audio with Whisper/GPT-4o transcribe via REST.","notes":"Whisper transcription costs about $0.006/min. TTS is billed per character or per token, depending on the model. Speech-to-text guide: https://developers.openai.com/api/docs/guides/speech-to-text.","verified":"2026-09-24","operations":["text-to-speech","speech-to-text"],"auth_scheme":{"type":"http","scheme":"bearer","format":"Authorization: Bearer <OPENAI_API_KEY>","source_url":"https://developers.openai.com/api/docs/guides/text-to-speech.md","checked_at":"2026-09-24"},"base_url":"https://api.openai.com/v1","rate_limits":{"summary":"Usage tiers (Free, Tier 1-5) set rate limits and monthly usage caps; Free tier capped at $100/month","source_url":"https://developers.openai.com/api/docs/guides/rate-limits.md","checked_at":"2026-09-24"},"data_policy":{"summary":"API data not used for training unless you opt in; abuse-monitoring logs retained by default (ZDR available to eligible customers)","source_url":"https://developers.openai.com/api/docs/guides/your-data.md","checked_at":"2026-09-24"},"no_auth":false,"has_free_tier":false,"has_trial":false,"no_card":false,"stale":false,"link_check":{"checked_at":"2026-09-24","docs":"ok","openapi":"ok","llms_txt":"ok"},"ratings":[{"source":"github","repo":"openai/openai-openapi","stars":2524,"forks":526,"pushed_at":"2026-09-23","archived":false,"url":"https://github.com/openai/openai-openapi","fetched_at":"2026-09-24T16:54Z"}],"uptime":{"window_days":30,"api":{"url":"https://api.openai.com/v1","probes":1,"up":1,"median_ms":268,"last":{"at":"2026-09-24T18:26Z","up":true,"detail":404}}}},
{"id":"resemble-ai-api","name":"Resemble AI API","homepage":"https://www.resemble.ai","docs":"https://docs.resemble.ai/","auth":"api_key","auth_hint":"API key from app.resemble.ai dashboard","mcp":{"type":"none","url":null,"maintainer":"none","source_url":"https://github.com/resemble-ai/resemble-mcp","checked_at":"2026-09-24","domain_verified":null,"kind":"none","config":null},"free_tier":"Paid only; Flex plan is $0/mo base with pay-as-you-go credits, no free usage allowance stated","sdk":[],"openapi":null,"llms_txt":null,"desc_en":"Synthesize speech, clone voices, convert speech-to-speech and detect deepfake audio via REST API.","notes":"Enterprise plans are available for on-prem deployment and custom model training. Vendor MCP at https://docs.resemble.ai/_mcp/server only searches the docs.","verified":"2026-09-24","operations":["text-to-speech","voice-cloning"],"free_plan":{"kind":"none","requires_card":false,"source_url":"https://www.resemble.ai/pricing","checked_at":"2026-09-24"},"auth_scheme":{"type":"http","scheme":"bearer","format":"Authorization: Bearer <API_KEY>","source_url":"https://docs.resemble.ai/getting-started/authentication.md","checked_at":"2026-09-24"},"rate_limits":{"summary":"About 40 requests/second per API token; audio enhancement 10 requests/minute","source_url":"https://docs.resemble.ai/getting-started/rate-limits.md","checked_at":"2026-09-24"},"no_auth":false,"has_free_tier":false,"has_trial":false,"no_card":false,"stale":false,"link_check":{"checked_at":"2026-09-24","docs":"ok","mcp":"ok"},"ratings":[{"source":"sourceforge","rating":1.7,"reviews":3,"url":"https://sourceforge.net/software/product/Resemble-AI/","fetched_at":"2026-09-24T16:56Z"}],"uptime":{"window_days":30,"mcp_remote":{"url":"https://docs.resemble.ai/_mcp/server","probes":1,"up":1,"median_ms":602,"last":{"at":"2026-09-24T18:26Z","up":true,"detail":200}}},"reviews_url":"https://raw.githubusercontent.com/eater2/ai_agents_api_library/main/catalog/reviews/resemble-ai-api.json"},
{"id":"rev-ai-api","name":"Rev AI API","homepage":"https://www.rev.ai","docs":"https://docs.rev.ai/","auth":"api_key","auth_hint":"Authorization: Bearer <access_token>","mcp":{"type":"none","url":null,"maintainer":"none","source_url":"https://docs.rev.ai/mcp","checked_at":"2026-09-24","domain_verified":null,"kind":"none","config":null},"free_tier":"trial credits (about 5 hours of ASR)","sdk":["python","node","java"],"openapi":null,"llms_txt":null,"desc_en":"Submit audio for asynchronous or streaming speech-to-text transcription, plus sentiment and topic extraction, via REST.","notes":"Vendor MCP at https://docs.rev.ai/mcp only searches the docs. Human transcription is sold separately as a paid option.","verified":"2026-09-24","operations":["speech-to-text"],"free_plan":{"kind":"trial","quota":"Free credits equivalent to 5 hours of Reverb ASR","period":"one_time","source_url":"https://www.rev.ai/pricing","checked_at":"2026-09-24"},"auth_scheme":{"type":"http","scheme":"bearer","format":"Authorization: Bearer <REVAI_ACCESS_TOKEN>","source_url":"https://docs.rev.ai/get-started.md","checked_at":"2026-09-24"},"base_url":"https://api.rev.ai/speechtotext/v1","rate_limits":{"summary":"Async STT: 10,000 transcription requests per 10 minutes per user; multipart uploads concurrency 5, 2 GB/file","source_url":"https://docs.rev.ai/api/asynchronous.md","checked_at":"2026-09-24"},"async_jobs":{"value":true,"how":"POST /jobs returns job id; poll GET /jobs/{id} then GET /jobs/{id}/transcript, or use webhook notification","source_url":"https://docs.rev.ai/get-started.md"},"data_policy":{"summary":"Jobs and associated data deleted after max 30 days; configurable earlier auto-delete or delete_after_seconds","source_url":"https://docs.rev.ai/api/security.md","checked_at":"2026-09-24"},"no_auth":false,"call":{"operation":"submit an async transcription job","method":"POST","url":"https://api.rev.ai/speechtotext/v1/jobs","example":"curl -X POST https://api.rev.ai/speechtotext/v1/jobs -H \"Authorization: Bearer $REVAI_ACCESS_TOKEN\" -H 'Content-Type: application/json' -d '{\"source_config\":{\"url\":\"https://www.rev.ai/FTC_Sample_1.mp3\"}}'","response_fields":["id","status","created_on"],"async":"poll GET https://api.rev.ai/speechtotext/v1/jobs/{id} until status is transcribed, then GET .../jobs/{id}/transcript (Accept: text/plain)","source_url":"https://docs.rev.ai/api/asynchronous/get-started/","checked_at":"2026-09-24"},"unit_price":{"summary":"Reverb ASR: $0.20 per hour English, $0.30 per hour other languages (per-second billing, 15 s minimum)","source_url":"https://www.rev.ai/pricing","checked_at":"2026-09-24"},"has_free_tier":false,"has_trial":true,"no_card":false,"stale":false,"link_check":{"checked_at":"2026-09-24","docs":"ok","mcp":"ok"},"uptime":{"window_days":30,"api":{"url":"https://api.rev.ai/speechtotext/v1","probes":1,"up":1,"median_ms":689,"last":{"at":"2026-09-24T18:26Z","up":true,"detail":404}}}},
{"id":"speechmatics-api","name":"Speechmatics API","homepage":"https://www.speechmatics.com","docs":"https://docs.speechmatics.com","auth":"api_key","auth_hint":"Authorization: Bearer <key>","mcp":{"type":"community","url":"https://github.com/ArchieMcM234/speechmatics_claude_code_mcp","maintainer":"community","repo":"https://github.com/ArchieMcM234/speechmatics_claude_code_mcp","tools":["transcribe_file","transcribe_directory","get_transcript","get_usage"],"covers_full_api":false,"source_url":"https://github.com/ArchieMcM234/speechmatics_claude_code_mcp","checked_at":"2026-09-24","domain_verified":null,"kind":"community","config":{"transport":"stdio","command":"uv","args":["--directory","/path/to/speechmatics_claude_code_mcp","run","python","server.py"],"env":["SPEECHMATICS_API_KEY"],"source_url":"https://github.com/ArchieMcM234/speechmatics_claude_code_mcp","docs_only":false,"checked_at":"2026-09-24"}},"free_tier":"Trial: one-time $100 credit grant, no payment card required","sdk":["python","javascript"],"openapi":null,"llms_txt":"https://docs.speechmatics.com/llms.txt","desc_en":"Transcribe audio in batch or real time with speaker diarization across many languages via REST/WebSocket.","notes":"The free tier also includes 2 concurrent real-time sessions. No official vendor MCP server was found.","verified":"2026-09-24","operations":["speech-to-text"],"free_plan":{"kind":"trial","requires_card":false,"quota":"$100 credit grant","period":"one_time","source_url":"https://docs.speechmatics.com/administration/plans.md","checked_at":"2026-09-24"},"auth_scheme":{"type":"http","scheme":"bearer","format":"Authorization: Bearer <API_KEY>","source_url":"https://docs.speechmatics.com/get-started/authentication.md","checked_at":"2026-09-24"},"base_url":"https://eu1.asr.api.speechmatics.com/v2","rate_limits":{"summary":"Batch: 10 new jobs/s, 50 job status requests/s; backstop 20,000 concurrent jobs; HTTP 429 when exceeded","source_url":"https://docs.speechmatics.com/speech-to-text/batch/limits.md","checked_at":"2026-09-24"},"async_jobs":{"value":true,"how":"Batch: POST /v2/jobs, then poll GET /v2/jobs/{id} or use Notifications (callbacks)","source_url":"https://docs.speechmatics.com/speech-to-text/batch/limits.md"},"no_auth":false,"call":{"operation":"transcribe an audio file (batch job, wait for result)","method":"POST","url":"https://eu1.asr.api.speechmatics.com/v2/jobs/?wait=60&format=txt","example":"curl -L -X POST \"https://eu1.asr.api.speechmatics.com/v2/jobs/?wait=60&format=txt\" -H \"Authorization: Bearer $SPEECHMATICS_API_KEY\" -F data_file=@example.wav -F config='{\"type\": \"transcription\", \"transcription_config\": {\"model\": \"enhanced\", \"language\": \"en\"}}'","response_fields":["id","status","txt"],"async":"if status is still created when wait elapses, GET /v2/jobs/{id}/transcript?format=txt (also accepts wait) until done","source_url":"https://docs.speechmatics.com/speech-to-text/batch/synchronous.md","checked_at":"2026-09-24"},"unit_price":{"summary":"Pro pay-as-you-go: batch Standard $0.24 per audio hour, batch Enhanced $0.40/hr, Melia 1 $0.129/hr; real-time Standard $0.24/hr, Enhanced $0.43/hr","source_url":"https://www.speechmatics.com/pricing","checked_at":"2026-09-24"},"has_free_tier":false,"has_trial":true,"no_card":true,"stale":false,"link_check":{"checked_at":"2026-09-24","docs":"ok","mcp":"ok","llms_txt":"ok"},"uptime":{"window_days":30,"api":{"url":"https://eu1.asr.api.speechmatics.com/v2","probes":1,"up":1,"median_ms":532,"last":{"at":"2026-09-24T18:26Z","up":true,"detail":200}}}}
]}