{ "name": "IBM watsonx Speech to Text", "slug": "ibm-watson-speech-to-text", "website_url": "https://www.ibm.com/products/speech-to-text", "vendor_description": "\"IBM Watson® Speech to Text technology enables fast and accurate speech transcription in multiple languages for a variety of use cases, including but not limited to customer self-service, agent assistance and speech analytics.\"", "categories": [ "speech-to-text" ], "summary": "IBM watsonx Speech to Text is a REST API for fast, accurate transcription supporting batch, streaming, and WebSocket modes, aimed at customer self-service, call-center analytics, captioning, and accessibility applications. Pricing starts at $0.02 per minute with a 500-minute free tier and no sales call required, scaling to enterprise plans with unlimited concurrency. Deployments are available across seven global regions, SDKs cover Python, Node.js, Java, Swift, and Go, and the service holds SOC 2 Type II, HIPAA, GDPR, and ISO 27001 certifications.", "capabilities": { "supported_actions": [ "transcribe_batch", "transcribe_streaming", "transcribe_websocket", "transcribe_async_http", "speaker_diarization", "word_timestamps", "interim_results", "keyword_spotting", "word_confidence_scores", "smart_formatting", "profanity_filtering", "custom_language_model", "custom_acoustic_model", "language_identification", "speech_activity_detection", "transcript_enrichment", "speech_begin_event_detection" ], "supported_regions": [ "us-south (Dallas)", "us-east (Washington DC)", "eu-de (Frankfurt)", "eu-gb (London)", "au-syd (Sydney)", "jp-tok (Tokyo)", "kr-seo (Seoul)" ], "supported_languages": [ "English (US)", "English (UK)", "English (Australian)", "English (Indian)", "French (France)", "French (Canadian)", "German", "Spanish (Castilian)", "Spanish (Argentinian)", "Spanish (Chilean)", "Spanish (Colombian)", "Spanish (Mexican)", "Spanish (Peruvian)", "Brazilian Portuguese", "Japanese", "Italian", "Dutch", "Swedish", "Arabic" ], "input_types": [ "audio/wav", "audio/mp3", "audio/mpeg", "audio/flac", "audio/ogg", "audio/ogg;codecs=opus", "audio/ogg;codecs=vorbis", "audio/webm", "audio/webm;codecs=opus", "audio/webm;codecs=vorbis", "audio/l16", "audio/alaw", "audio/mulaw", "audio/basic", "audio/g729", "WebSocket streaming", "HTTP REST (batch)", "Asynchronous HTTP with callback URL" ], "output_types": [ "JSON transcript", "word timestamps", "word confidence scores", "speaker labels (diarization)", "keyword spotting results", "interim results", "WebVTT captions (via IBM Video Streaming integration)" ], "webhooks_supported": true, "sandbox_available": false, "sdk_languages": [ "Python", "Node.js", "Java", "Swift", "Go" ], "mcp_server_available": false }, "integration": { "api_style": "rest", "base_url": "https://api.{location}.speech-to-text.watson.cloud.ibm.com/instances/{instance_id}", "api_version": "v1", "versioning_scheme": "url", "stability": "ga", "deprecation_policy_url": "https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-release-notes", "auth_methods": [ "api_key", "oauth2" ], "auth_docs_url": "https://cloud.ibm.com/docs/watson?topic=watson-iam", "idempotency_supported": false, "error_format": "vendor-specific", "webhook_signing": "hmac_sha1", "webhook_events_url": "https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-async", "rate_limit_requests": null, "rate_limit_window": null, "sdk_packages": [ { "package": "ibm-watson", "language": "Python", "official": true, "repo_url": "https://github.com/watson-developer-cloud/python-sdk" }, { "package": "ibm-watson", "language": "Node.js", "official": true, "repo_url": "https://github.com/watson-developer-cloud/node-sdk" }, { "package": "com.ibm.watson:ibm-watson", "language": "Java", "official": true, "repo_url": "https://github.com/watson-developer-cloud/java-sdk" }, { "package": "IBMWatsonSpeechToTextV1", "language": "Swift", "official": true, "repo_url": "https://github.com/watson-developer-cloud/swift-sdk" }, { "package": "github.com/watson-developer-cloud/go-sdk/v2", "language": "Go", "official": true, "repo_url": "https://github.com/watson-developer-cloud/go-sdk" } ], "mcp_url": null, "quickstart_url": "https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-gettingStarted" }, "pricing": { "pricing_model": "usage_based", "has_published_pricing": true, "starting_price_usd": "0.0200", "price_basis": "minute", "free_tier_available": true, "free_tier_limit": "500 minutes/month", "free_tier_details": "Lite plan: 500 minutes per month at no cost (recurring monthly allowance). No customization access on Lite; service deleted after 30 days of inactivity. Plus plan (paid, no base fee): first 1–999,999 minutes at $0.02 USD/minute, 1,000,000+ minutes at $0.01 USD/minute. Premium plan (requires sales contact) includes first 150,000 minutes/month at no charge; pricing beyond that is not publicly disclosed.", "minimum_commitment": null, "self_serve_signup": true, "requires_sales_call": false, "requires_verification": false, "enterprise_plan_available": true, "price_points": [ { "plan": "Lite", "item": "Speech recognition", "amount_usd": "0.0000", "amount_percent": null, "per": "500 minutes per month (recurring free allowance)", "currency": "USD", "source_url": "https://github.com/ibm-cloud-docs/speech-to-text/blob/master/faq-pricing.md" }, { "plan": "Plus", "item": "Speech recognition", "amount_usd": "0.0200", "amount_percent": null, "per": "minute (1–999,999 minutes/month)", "currency": "USD", "source_url": "https://github.com/ibm-cloud-docs/speech-to-text/blob/master/faq-pricing.md" }, { "plan": "Plus", "item": "Speech recognition", "amount_usd": "0.0100", "amount_percent": null, "per": "minute (1,000,000+ minutes/month)", "currency": "USD", "source_url": "https://github.com/ibm-cloud-docs/speech-to-text/blob/master/faq-pricing.md" }, { "plan": "Premium", "item": "Speech recognition (first 150,000 minutes/month included)", "amount_usd": "0.0000", "amount_percent": null, "per": "month (first 150,000 minutes at no charge; beyond that requires sales contact)", "currency": "USD", "source_url": "https://github.com/ibm-cloud-docs/speech-to-text/blob/master/faq-pricing.md" } ] }, "compliance": { "soc2": "type_2", "hipaa": true, "gdpr": true, "iso_27001": true, "pci_dss": null, "sla_published": true, "sla_url": "https://cloud.ibm.com/docs/overview?topic=overview-slas", "data_retention_policy_url": "https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-information-security", "documented_rate_limits": "Lite plan: 500 minutes/month. Plus plan: maximum 100 concurrent transcription requests. Premium plan: unlimited concurrent transcription requests. No explicit per-request rate limit documented publicly beyond concurrency caps.", "known_restrictions": [ "Lite plan services deleted after 30 days of inactivity", "Lite plan has no access to customization (custom language/acoustic models)", "Standard plan no longer available for new purchases", "Smart formatting limited to US English and Spanish", "Profanity filter available for US English only", "Speaker diarization language support varies by model generation", "Audio billed by the minute including silence", "Custom model training requires a paid plan (Plus or Premium)", "Premium plan requires direct IBM sales contact for provisioning" ] }, "developer": { "docs_url": "https://developer.ibm.com/", "api_reference_url": "https://cloud.ibm.com/apidocs/speech-to-text", "openapi_spec_url": null, "postman_collection_url": null, "changelog_url": null, "status_page_url": null, "llms_txt_url": null, "markdown_docs_url": null, "rendering": "static" }, "adoption": { "launched_at": "2015-01-01", "ga_date": "2024-08-23", "github_stars": null, "github_stars_at": null, "notable_customers": [ "Citibank", "Bradesco", "Humana" ] }, "scores": { "agent_friendliness": 30, "pricing_transparency": 100, "setup_speed": 85, "docs_quality": 35, "procurement_friction": 100, "trust_readiness": 90, "best_for": [ "Prototypes and side projects - free to start, no sales call", "Regulated or enterprise workloads - compliance attestations and an enterprise plan", "Teams needing broad API coverage out of the box" ], "avoid_if": [] }, "sources": [ { "field": "vendor_description", "url": "https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-about", "excerpt": "IBM Watson® Speech to Text technology enables fast and accurate speech transcription in multiple languages for a variety of use cases, including but not limited to customer self-service, agent assistance and speech analytics.", "confidence": "high" }, { "field": "pricing_model", "url": "https://github.com/ibm-cloud-docs/speech-to-text/blob/master/faq-pricing.md", "excerpt": "Plus Plan: Tiered pricing: $0.02 (USD) per minute for 1-999,999 minutes monthly; $0.01 (USD) per minute for 1M+ minutes. No base subscription fee mentioned.", "confidence": "high" }, { "field": "free_tier_available", "url": "https://github.com/ibm-cloud-docs/speech-to-text/blob/master/faq-pricing.md", "excerpt": "Lite Plan: 500 minutes per month at no cost. No customization access. Services deleted after 30 days of inactivity.", "confidence": "high" }, { "field": "sandbox_available", "url": "https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-faq-pricing", "excerpt": "The Lite plan is free and provides 500 minutes of speech recognition per month at no cost.", "confidence": "high" }, { "field": "soc2", "url": "https://www.ibm.com/products/cloud/compliance/soc-2", "excerpt": "IBM Cloud is SOC 2 compliant because it has implemented and maintained robust controls that meet SOC 2 requirements, and it undergoes regular, independent audits. Services issue SOC 2 Type 2 reports at least once each year.", "confidence": "high" }, { "field": "hipaa", "url": "https://github.com/ibm-cloud-docs/speech-to-text/blob/master/faq-pricing.md", "excerpt": "Premium Plan: HIPAA readiness support. Enterprise features: data isolation, encryption key management, mutual authentication.", "confidence": "high" }, { "field": "vendor_description", "url": "https://www.ibm.com/products/speech-to-text", "excerpt": "IBM Watson® Speech to Text technology enables fast and accurate speech transcription in multiple languages for a variety of use cases, including but not limited to customer self-service, agent assistance and speech analytics.", "confidence": "high" }, { "field": "pricing_model", "url": "https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-faq-pricing", "excerpt": "For the Plus plan, pricing starts at $0.02 USD per minute for 1 - 999,999 minutes used, and $0.01 USD per minute for 1,000,000+ minutes.", "confidence": "high" }, { "field": "free_tier_available", "url": "https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-faq-pricing", "excerpt": "The Lite plan is free and provides 500 minutes of speech recognition per month at no cost.", "confidence": "high" }, { "field": "enterprise_plan_available", "url": "https://github.com/ibm-cloud-docs/speech-to-text/blob/master/faq-pricing.md", "excerpt": "Premium Plan: All Plus plan features included. First 150,000 minutes monthly at no charge. Enterprise features: data isolation, encryption key management, mutual authentication. HIPAA readiness support. Requires direct sales contact for provisioning.", "confidence": "high" }, { "field": "soc2", "url": "https://www.ibm.com/new/announcements/ibm-public-cloud-soc-framework", "excerpt": "IBM Public Cloud Services Added to SOC 1 Type 2, SOC 2 Type 2, and SOC 3 Reports", "confidence": "high" }, { "field": "hipaa", "url": "https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-information-security", "excerpt": "IBM is committed to providing clients and partners with innovative data privacy, security and governance solutions to assist them on their journey to GDPR compliance. IBM clients who are subject to HIPAA and who wish to use IBM Cloud products for HIPAA regulated data must enter into a Business Associate Agreement (BAA) with IBM.", "confidence": "high" }, { "field": "iso_27001", "url": "https://www.ibm.com/support/pages/ibm-iso-27001-certifications-cloud", "excerpt": "IBM has obtained certificates to the ISO 27001 standard by country or business unit. IBM ISO 27001 certificates are published and generally available.", "confidence": "high" }, { "field": "pci_dss", "url": "https://www.ibm.com/products/cloud/compliance/pci", "excerpt": "IBM Cloud PCI DSS compliance", "confidence": "low" }, { "field": "documented_rate_limits", "url": "https://github.com/ibm-cloud-docs/speech-to-text/blob/master/faq-pricing.md", "excerpt": "Maximum of 100 concurrent transcription requests [Plus plan]. Premium plan includes unlimited concurrent transcriptions.", "confidence": "high" }, { "field": "supported_languages", "url": "https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-models-ng", "excerpt": "The service supports speech recognition for numerous languages including English (US, Australian, Indian, UK dialects), Japanese, French (France, Canadian), German, Spanish (Castilian, Argentinian, Chilean, Colombian, Mexican, Peruvian), Brazilian Portuguese, Dutch, Italian, Swedish, Arabic.", "confidence": "high" }, { "field": "supported_regions", "url": "https://cloud.ibm.com/apidocs/speech-to-text", "excerpt": "IBM Watson Speech to Text is available in the following regions: Dallas (us-south), Washington DC (us-east), Frankfurt (eu-de), Sydney (au-syd), Tokyo (jp-tok), London (eu-gb), Seoul (kr-seo).", "confidence": "high" }, { "field": "sdk_languages", "url": "https://cloud.ibm.com/apidocs/speech-to-text", "excerpt": "IBM Watson Speech to Text provides client libraries for Java, Node.js, Python, Ruby, Go, and .NET Standard.", "confidence": "high" }, { "field": "mcp_server_available", "url": "https://github.com/IBM/ibm-watsonxdata-mcp-server", "excerpt": "IBM has an MCP server for watsonx.data but no official MCP server for Watson Speech to Text was found in IBM's official repositories or documentation.", "confidence": "high" }, { "field": "output_types", "url": "https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-output", "excerpt": "IBM Watson Speech to Text returns JSON response content. The service reports word timestamps, word confidence scores, speaker labels (diarization), and keyword spotting results.", "confidence": "high" }, { "field": "supported_actions", "url": "https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-about", "excerpt": "IBM provides the Watson speech-to-text service over several different channels, such as REST, HTTP with webhook callbacks, and WebSockets.", "confidence": "high" }, { "field": "known_restrictions", "url": "https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-about", "excerpt": "Smart formatting to control how the engine transcribes numbers and dates for U.S. English and Spanish. Profanity filter censors profanity from US English transcriptions by default.", "confidence": "high" }, { "field": "self_serve_signup", "url": "https://cloud.ibm.com/catalog/services/speech-to-text", "excerpt": "Speech to Text - IBM Cloud catalog listing allows self-serve signup for Lite and Plus plans directly through IBM Cloud.", "confidence": "high" }, { "field": "base_url", "url": "https://cloud.ibm.com/apidocs/speech-to-text", "excerpt": "The Dallas base URL for Speech to Text is https://api.us-south.speech-to-text.watson.cloud.ibm.com", "confidence": "high" }, { "field": "versioning_scheme", "url": "https://github.com/ibm-cloud-docs/speech-to-text/blob/master/websockets.md", "excerpt": "wss://api.{location}.speech-to-text.watson.cloud.ibm.com/instances/{instance_id}/v1/recognize", "confidence": "high" }, { "field": "api_style", "url": "https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-websockets", "excerpt": "The WebSocket interface", "confidence": "high" }, { "field": "auth_methods", "url": "https://github.com/watson-developer-cloud/python-sdk", "excerpt": "The SDK supports authentication methods including IAM, username/password, bearer tokens, and Cloud Pak for Data authentication.", "confidence": "high" }, { "field": "stability", "url": "https://github.com/ibm-cloud-docs/speech-to-text/blob/master/release-notes.md", "excerpt": "23 August 2024: All large speech models transitioned to GA status", "confidence": "high" }, { "field": "sdk_packages", "url": "https://github.com/watson-developer-cloud/node-sdk", "excerpt": "NPM Package Name: ibm-watson. Official IBM Watson SDK for Node.js", "confidence": "high" }, { "field": "quickstart_url", "url": "https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-gettingStarted", "excerpt": "Getting started with Speech to Text | IBM Cloud Docs", "confidence": "high" }, { "field": "webhook_events_url", "url": "https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-async", "excerpt": "The asynchronous HTTP interface", "confidence": "high" }, { "field": "price_basis", "url": "https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-faq-pricing", "excerpt": "For the Plus plan, pricing starts at $0.02 USD per minute for 1 - 999,999 minutes used", "confidence": "high" }, { "field": "launched_at", "url": "https://github.com/ibm-cloud-docs/speech-to-text/blob/master/release-notes.md", "excerpt": "The release notes document extends back to 2015, indicating the service has been available since at least that year.", "confidence": "medium" }, { "field": "gdpr", "url": "https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-information-security", "excerpt": "IBM is committed to providing clients and partners with innovative data privacy, security and governance solutions to assist them on their journey to GDPR compliance.", "confidence": "high" }, { "field": "iso_27001", "url": "https://www.ibm.com/products/cloud/compliance/iso-27001", "excerpt": "What is ISO/IEC 27001? | IBM", "confidence": "high" }, { "field": "sla_published", "url": "https://cloud.ibm.com/docs/overview?topic=overview-slas", "excerpt": "IBM provides a 99.9% uptime availability SLA for Watson Services in Premium or Dedicated deployment models configured for high availability if the services are provisioned across multiple environments in geographically separated data-centers within one IBM-specified Region.", "confidence": "high" }, { "field": "documented_rate_limits", "url": "https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-faq-pricing", "excerpt": "Plus version includes unlimited minutes per month and 100 concurrent transcriptions, and the Premium plan includes unlimited minutes per month and unlimited concurrent transcriptions.", "confidence": "high" }, { "field": "supported_languages", "url": "https://github.com/ibm-cloud-docs/speech-to-text/blob/master/release-notes.md", "excerpt": "Large speech model for Italian, it-IT is now generally available (GA) as of May 2026, supporting both 8kHz and 16kHz audio.", "confidence": "high" }, { "field": "webhooks_supported", "url": "https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-basic-request", "excerpt": "The service registers a callback URL for use with subsequent asynchronous recognition requests. The service attempts to register or allowlist the callback URL if it is not already registered by sending a GET request to the callback URL.", "confidence": "high" }, { "field": "sdk_languages", "url": "https://watson-developer-cloud.github.io/swift-sdk/services/SpeechToTextV1/index.html", "excerpt": "SpeechToTextV1 Reference — Watson Developer Cloud Swift SDK", "confidence": "high" }, { "field": "input_types", "url": "https://github.com/ibm-cloud-docs/speech-to-text/blob/master/audio-formats.md", "excerpt": "The IBM Watson Speech to Text service supports these audio input formats: audio/wav, audio/mp3, audio/mpeg, audio/flac, audio/ogg (Opus and Vorbis codecs), audio/webm (Opus and Vorbis codecs), audio/l16, audio/alaw, audio/mulaw, audio/basic, audio/g729.", "confidence": "high" }, { "field": "supported_actions", "url": "https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-output", "excerpt": "Keyword spotting identifies spoken phrases from the audio that match specified keyword strings. Word timestamps reports confidence levels for each word. Profanity filter censors profanity from US English transcriptions.", "confidence": "high" }, { "field": "known_restrictions", "url": "https://github.com/ibm-cloud-docs/speech-to-text/blob/master/faq-pricing.md", "excerpt": "Lite Plan: No customization access. Services deleted after 30 days of inactivity. Billing: Monthly aggregation rounded to nearest minute; all audio (including silence) counts toward usage totals.", "confidence": "high" }, { "field": "categories", "url": "https://www.ibm.com/products/speech-to-text", "excerpt": "IBM Watson® Speech to Text technology enables fast and accurate speech transcription in multiple languages for a variety of use cases, including but not limited to customer self-service, agent assistance and speech analytics.", "confidence": "high" }, { "field": "base_url", "url": "https://github.com/ibm-cloud-docs/speech-to-text/blob/master/websockets.md", "excerpt": "wss://api.{location}.speech-to-text.watson.cloud.ibm.com/instances/{instance_id}/v1/recognize", "confidence": "high" }, { "field": "api_version", "url": "https://github.com/ibm-cloud-docs/speech-to-text/blob/master/websockets.md", "excerpt": "The path explicitly includes \"/v1/recognize\", indicating API version 1 endpoints for speech recognition services.", "confidence": "high" }, { "field": "api_style", "url": "https://cloud.ibm.com/apidocs/speech-to-text", "excerpt": "Speech to Text | IBM Cloud API Docs", "confidence": "high" }, { "field": "auth_methods", "url": "https://github.com/ibm-cloud-docs/speech-to-text/blob/master/websockets.md", "excerpt": "Pass a valid access token to establish an authenticated connection with the service.", "confidence": "high" }, { "field": "auth_docs_url", "url": "https://cloud.ibm.com/docs/watson?topic=watson-iam", "excerpt": "Authenticating to Watson services", "confidence": "high" }, { "field": "sdk_packages", "url": "https://github.com/watson-developer-cloud/python-sdk", "excerpt": "PyPI Package Name: ibm-watson. This is the official IBM Watson Python SDK, maintained by the watson-developer-cloud organization on GitHub.", "confidence": "high" }, { "field": "sdk_packages", "url": "https://github.com/watson-developer-cloud/java-sdk", "excerpt": "Maven Package Name: com.ibm.watson:ibm-watson. This is IBM's official Java SDK for Watson services, maintained by the watson-developer-cloud organization.", "confidence": "high" }, { "field": "webhook_signing", "url": "https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-async", "excerpt": "If you specify a user secret with the request, IBM Watson Speech to Text service uses it as a key to calculate an HMAC-SHA1 signature of the challenge string in its response to the POST request, and sends this signature in the X-Callback-Signature header", "confidence": "high" }, { "field": "starting_price_usd", "url": "https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-faq-pricing", "excerpt": "For the Plus plan, pricing starts at $0.02 USD per minute for 1 - 999,999 minutes used, and $0.01 USD per minute for 1,000,000+ minutes.", "confidence": "high" }, { "field": "free_tier_limit", "url": "https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-faq-pricing", "excerpt": "The Lite plan is free and provides 500 minutes of speech recognition per month at no cost.", "confidence": "high" }, { "field": "ga_date", "url": "https://github.com/ibm-cloud-docs/speech-to-text/blob/master/release-notes.md", "excerpt": "23 August 2024: All large speech models transitioned to GA status", "confidence": "high" }, { "field": "notable_customers", "url": "https://nexright.com/ibm-watson-speech-to-text-enterprise-scale/", "excerpt": "Bradesco reduced response times by an impressive 95%. Humana's voice agent, powered by IBM Watson Speech, handles 7,000 live calls per day from healthcare providers", "confidence": "medium" }, { "field": "sla_url", "url": "https://cloud.ibm.com/docs/overview?topic=overview-slas", "excerpt": "Understanding IBM Cloud service level agreements", "confidence": "medium" }, { "field": "notable_customers", "url": "https://www.ibm.com/blogs/watson/2017/01/level-7-systems-wins-customers-watson-speech-text-api/", "excerpt": "Citibank built an analytics solution using Watson Speech to Text to transcribe and audit tens of thousands of customer calls, saving their auditors over 100,000 hours per month.", "confidence": "medium" }, { "field": "data_retention_policy_url", "url": "https://github.com/ibm-cloud-docs/speech-to-text/blob/master/data-security.md", "excerpt": "Results from synchronous HTTP and WebSocket requests are never stored to disk. Results from asynchronous HTTP requests are deleted as soon as their time to live expires.", "confidence": "high" }, { "field": "error_format", "url": "https://cloud.ibm.com/apidocs/speech-to-text", "excerpt": "Speech to Text | IBM Cloud API Docs", "confidence": "low" } ], "fields_not_found": [ "pci_dss (IBM Cloud has PCI DSS compliance broadly but Watson Speech to Text is not explicitly listed as a covered AOC service)", "exact Lite plan concurrency limit", "maximum audio file size limit for batch HTTP", "sandbox/test-mode API keys separate from production", "rate_limit_requests", "rate_limit_window", "idempotency_supported", "mcp_url", "deprecation_policy_url" ], "source_confidence": "high", "last_verified_at": "2026-06-21T00:00:00.000Z", "contribute": { "note": "This data is crowd-editable. Suggest corrections or leave a review via these endpoints - no auth required, requests are rate-limited, and every submission is reviewed before it goes live. For a field edit, {field} is any key in this response and a citation is required.", "endpoints": [ { "action": "review", "label": "Leave a review or comment", "method": "POST", "url": "https://apio.sh/api/feedback/ibm-watson-speech-to-text", "example_body": { "kind": "review", "rating": 5, "body": "Your experience with this API…" } }, { "action": "field_edit", "label": "Suggest a correction to a field (cite a source)", "method": "POST", "url": "https://apio.sh/api/suggest/ibm-watson-speech-to-text/{field}", "example_body": { "value": "corrected value", "citations": [ { "url": "https://source.example/page", "excerpt": "supporting quote" } ], "note": "what changed and why" } }, { "action": "new_api", "label": "Suggest a new API to add (only name is required - send as much as you can cite)", "method": "POST", "url": "https://apio.sh/api/suggest/api", "example_body": { "value": { "name": "Acme Email API", "website_url": "https://acme.example", "vendor_name": "Acme", "categories": [ "email" ], "pricing_model": "usage_based", "has_published_pricing": true, "free_tier_available": true, "price_points": [ { "plan": "Pay as you go", "item": "1,000 emails", "amount_usd": 1, "per": "1,000 emails", "source_url": "https://acme.example/pricing" } ], "soc2": "type_2", "docs_url": "https://docs.acme.example" }, "citations": [ { "url": "https://acme.example/pricing", "excerpt": "$1 per 1,000 emails" } ] }, "value_schema": [ { "field": "name", "type": "string", "label": "Product name (the only required field)" }, { "field": "website_url", "type": "string", "label": "Marketing website URL" }, { "field": "vendor_name", "type": "string", "label": "Company/vendor name behind the product" }, { "field": "vendor_description", "type": "string", "label": "One-line description, quoted from the vendor" }, { "field": "categories", "type": "string[]", "label": "Category/leaf slugs it belongs to, e.g. [\"email\",\"sms\"]" }, { "field": "primary_use_cases", "type": "string[]", "label": "What it's used for" }, { "field": "supported_actions", "type": "string[]", "label": "Concrete API actions/capabilities" }, { "field": "supported_regions", "type": "string[]", "label": "Countries/regions/data-residency" }, { "field": "supported_languages", "type": "string[]", "label": "Human/spoken languages supported" }, { "field": "input_types", "type": "string[]", "label": "Accepted input types/formats" }, { "field": "output_types", "type": "string[]", "label": "Produced output types/formats" }, { "field": "webhooks_supported", "type": "bool", "label": "Supports webhooks?" }, { "field": "sandbox_available", "type": "bool", "label": "Dedicated sandbox/test mode?" }, { "field": "sdk_languages", "type": "string[]", "label": "Languages with an official SDK" }, { "field": "mcp_server_available", "type": "bool", "label": "Official MCP server?" }, { "field": "pricing_model", "type": "enum", "label": "Pricing model", "values": [ "usage_based", "subscription", "seat_based", "hybrid", "contact_sales" ] }, { "field": "has_published_pricing", "type": "bool", "label": "Concrete prices published publicly?" }, { "field": "free_tier_available", "type": "bool", "label": "Recurring/perpetual free tier (not a trial)?" }, { "field": "free_tier_details", "type": "string", "label": "What the free tier includes" }, { "field": "minimum_commitment", "type": "string", "label": "Any stated minimum spend/commitment" }, { "field": "self_serve_signup", "type": "bool", "label": "Get an API key without talking to sales?" }, { "field": "requires_sales_call", "type": "bool", "label": "Does going live require sales?" }, { "field": "enterprise_plan_available", "type": "bool", "label": "Named enterprise tier?" }, { "field": "starting_price_usd", "type": "number", "label": "Lowest published paid entry price (USD number)" }, { "field": "price_basis", "type": "string", "label": "Unit the starting price is per, e.g. '1,000 emails'" }, { "field": "free_tier_limit", "type": "string", "label": "Free-tier ceiling in literal terms" }, { "field": "price_points", "type": "object[]", "label": "Structured prices: [{plan,item,amount_usd,amount_percent,per,source_url}]" }, { "field": "soc2", "type": "enum", "label": "SOC 2 status", "values": [ "type_2", "type_1", "in_progress", "none", "unknown" ] }, { "field": "hipaa", "type": "bool", "label": "HIPAA (e.g. BAA available)?" }, { "field": "gdpr", "type": "bool", "label": "GDPR compliance stated?" }, { "field": "iso_27001", "type": "bool", "label": "ISO 27001 certified?" }, { "field": "pci_dss", "type": "bool", "label": "PCI DSS compliant?" }, { "field": "sla_published", "type": "bool", "label": "Published SLA / uptime commitment?" }, { "field": "documented_rate_limits", "type": "string", "label": "Documented rate limits, quoted" }, { "field": "known_restrictions", "type": "string[]", "label": "Notable documented restrictions/limits" }, { "field": "auth_methods", "type": "string[]", "label": "Auth methods", "values": [ "api_key", "oauth2", "jwt", "basic", "hmac_signature", "mtls", "session" ] }, { "field": "api_style", "type": "enum", "label": "Primary API style", "values": [ "rest", "graphql", "grpc", "soap", "websocket" ] }, { "field": "base_url", "type": "string", "label": "API root/base URL" }, { "field": "api_version", "type": "string", "label": "Current API version string" }, { "field": "quickstart_url", "type": "string", "label": "Quickstart / hello-world URL" }, { "field": "docs_url", "type": "string", "label": "Developer docs URL" }, { "field": "api_reference_url", "type": "string", "label": "API reference URL" }, { "field": "openapi_spec_url", "type": "string", "label": "OpenAPI spec URL" }, { "field": "changelog_url", "type": "string", "label": "Changelog URL" }, { "field": "status_page_url", "type": "string", "label": "Status page URL" }, { "field": "notable_customers", "type": "string[]", "label": "Named public customers" }, { "field": "launched_at", "type": "string", "label": "Launch date (ISO date or year)" } ] }, { "action": "token", "label": "Optional - raise your rate limit", "method": "GET", "url": "https://apio.sh/api/feedback/token" } ] } }