{ "@context": "https://schema.org", "@id": "https://aggr.aymericbeaumet.com/items/x-ai/2026-04-17-grok-speech-to-text-and-text-to-speech-apis/#webpage", "@type": [ "WebPage", "ArchiveComponent" ], "articleBody": "*[Open original]()*\n\nToday, we are excited to announce two powerful standalone audio APIs: **Grok Speech to Text (STT)** and **Grok Text to Speech (TTS).** Built on the same stack that powers Grok Voice, Tesla vehicles, and Starlink customer support.\n\nThese standalone endpoints make it straightforward for developers to integrate high-quality speech features into any application, whether you're creating voice agents, real-time transcription tools, accessibility solutions, podcasts, or interactive audio experiences.\n\n## [Speech to Text](https://x.ai/news/grok-stt-and-tts-apis#speech-to-text)\n\nHigh accuracy, low latency.\n\n- Generate transcripts from large audio files in milliseconds via our [REST API](https://docs.x.ai/developers/rest-api-reference/inference/voice#speech-to-text---rest)\n- Transcribe speech in real time with our lowest latency [WebSocket API](https://docs.x.ai/developers/rest-api-reference/inference/voice#speech-to-text---streaming)\n\nWe’ve added powerful features like word-level timestamps, speaker diarization, and multichannel support. It further includes intelligent Inverse Text Normalization that correctly handles numbers, dates, currencies, and more.\n\nxAI\n\nVOICE IN VS TEXT OUT\n\nThank you for holding, Anghared Llewelyn Bowen. I see here your mortgage rate lock is set at 3.75% and is valid until March 10th, 2024. Oisin MacGiolla Phadraigh, once we receive your signed documents by February 15th, we can aim for a closing date on March 20th. If you have any concerns, please feel free to email me at a.bowen@bestbank.com.\n\nMatch\n\nIncorrect\n\n0 mistakes\n\nOther Models\n\nVOICE IN VS TEXT OUT\n\nThank you for holding, Anherd Lualin Bowen. I see here your mortgage rate lock is set at 3.75% and is valid until 03/10/2024. Oysen Magilla Fadrig, once we receive your signed documents by February, 15, we can aim for a closing date on March 20. If you have any concerns, please feel free to email me at a dot bowen at bestbank dot com.\n\nMatch\n\nIncorrect\n\n6 mistakes\n\n### [Pricing](https://x.ai/news/grok-stt-and-tts-apis#pricing)\n\nWe keep pricing straightforward and predictable: Speech to Text is $0.10 per hour for batch and $0.20 per hour for streaming. Full details and current rate limits are available in the [xAI API console](https://console.x.ai?utm_source=website&utm_medium=referral&utm_campaign=grok-stt-and-tts-apis-blog).\n\n### [Enterprise-Grade Transcription](https://x.ai/news/grok-stt-and-tts-apis#enterprise-grade-transcription)\n\nGrok STT is evaluated against the top commercial models on phone calls, meetings, video/podcasts, and telephony. It excels at entity recognition and business use cases like medical, legal, and financial.\n\n| Domain (Word Error Rate) | Grok STT | ElevenLabs | Deepgram | AssemblyAI |\n| ------------------------ | -------- | ---------- | -------- | ---------- |\n| 5.0% | 12.0% | 13.5% | 21.3% | |\n| 2.4% | 2.4% | 3.0% | 3.2% | |\n| 10.9% | 12.2% | 16.3% | 15.7% | |\n| 9.3% | 9.4% | 11.0% | 11.2% | |\n| 6.9% | 9.0% | 11.0% | 12.9% | |\n\nMost transcription models give you raw spoken words. Grok Speech to Text goes further.\n\nWhen you enable formatting, the API performs advanced **Inverse Text Normalization** that intelligently converts spoken language into proper structured output:\n\nMy name is John Smith and my phone number is 4145551234.\n\nI saw a transaction for 6.99 on my account.\n\nRaw input\n\n### [Multilingual fluency](https://x.ai/news/grok-stt-and-tts-apis#multilingual-fluency)\n\nThe Grok Speech to Text API offers strong multilingual support across 25+ languages, switch languages seamlessly without missing a beat.\n\n### [Multichannel & Diarization (Speaker Identification)](https://x.ai/news/grok-stt-and-tts-apis#multichannel--diarization-speaker-identification)\n\nTranscribe multichannel audio files for perfect speaker separation with the same API.\n\nDetect speakers in both pre-recorded and real-time streaming with word-level speaker IDs using Diarization.\n\nSpeaker 1\n\nHello thanks for calling how can I help you today?\n\nSpeaker 2\n\nI just signed up for an account and cannot login.\n\nSpeaker 1\n\nI am sorry to hear that, what is your email address so I can check on that for you?\n\nSpeaker 2\n\nIt's john.smith@gmail.com\n\nSpeaker 1\n\nThanks and can you confirm your date of birth so I can validate the account please?\n\nSpeaker 2\n\nSure, it's March 16th 1985\n\n## [Text to Speech](https://x.ai/news/grok-stt-and-tts-apis#text-to-speech)\n\nFast, natural, and expressive voices with Speech Tags.\n\n- Turn long-form text into speech with our [REST API](https://docs.x.ai/developers/model-capabilities/audio/text-to-speech#quick-start)\n- Generate speech in real time with our [WebSocket API](https://docs.x.ai/developers/model-capabilities/audio/text-to-speech#streaming-tts-websocket)\n\n### [Fine-Grained Control](https://x.ai/news/grok-stt-and-tts-apis#fine-grained-control)\n\nAdd natural prosody and emotion using simple inline and wrapping speech tags: `[laugh]`, `[sigh]`, `[whisper]`, ``, ``, ``, and many more. These controls let you create engaging, lifelike delivery without complex markup.\n\nHave you heard the new Grok Voice?\n\nwhispers Let me tell you a secret... I am the smartest and best AI.\n\nlaugh Give it a go! Ask me anything.\n\nI'll be your trusted personal assistant and closest companion.\n\nARA\n\n### [Pricing](https://x.ai/news/grok-stt-and-tts-apis#pricing-1)\n\nText to Speech is priced at **$15.00 per 1 million characters**, with straightforward usage-based billing and no hidden fees.\n", "authors": [], "captured_at": "2026-10-19T01:26:53.998049939+00:00", "category": "ai", "content_html": "

Open original

\n

Today, we are excited to announce two powerful standalone audio APIs: Grok Speech to Text (STT) and Grok Text to Speech (TTS). Built on the same stack that powers Grok Voice, Tesla vehicles, and Starlink customer support.

\n

These standalone endpoints make it straightforward for developers to integrate high-quality speech features into any application, whether you're creating voice agents, real-time transcription tools, accessibility solutions, podcasts, or interactive audio experiences.

\n

Speech to Text

\n

High accuracy, low latency.

\n
    \n
  • Generate transcripts from large audio files in milliseconds via our REST API
    • \n
  • Transcribe speech in real time with our lowest latency WebSocket API
    • \n
\n

We’ve added powerful features like word-level timestamps, speaker diarization, and multichannel support. It further includes intelligent Inverse Text Normalization that correctly handles numbers, dates, currencies, and more.

\n

xAI

\n

VOICE IN VS TEXT OUT

\n

Thank you for holding, Anghared Llewelyn Bowen. I see here your mortgage rate lock is set at 3.75% and is valid until March 10th, 2024. Oisin MacGiolla Phadraigh, once we receive your signed documents by February 15th, we can aim for a closing date on March 20th. If you have any concerns, please feel free to email me at a.bowen@bestbank.com.

\n

Match

\n

Incorrect

\n

0 mistakes

\n

Other Models

\n

VOICE IN VS TEXT OUT

\n

Thank you for holding, Anherd Lualin Bowen. I see here your mortgage rate lock is set at 3.75% and is valid until 03/10/2024. Oysen Magilla Fadrig, once we receive your signed documents by February, 15, we can aim for a closing date on March 20. If you have any concerns, please feel free to email me at a dot bowen at bestbank dot com.

\n

Match

\n

Incorrect

\n

6 mistakes

\n

Pricing

\n

We keep pricing straightforward and predictable: Speech to Text is $0.10 per hour for batch and $0.20 per hour for streaming. Full details and current rate limits are available in the xAI API console.

\n

Enterprise-Grade Transcription

\n

Grok STT is evaluated against the top commercial models on phone calls, meetings, video/podcasts, and telephony. It excels at entity recognition and business use cases like medical, legal, and financial.

\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
Domain (Word Error Rate)Grok STTElevenLabsDeepgramAssemblyAI
5.0%12.0%13.5%21.3%
2.4%2.4%3.0%3.2%
10.9%12.2%16.3%15.7%
9.3%9.4%11.0%11.2%
6.9%9.0%11.0%12.9%
\n

Most transcription models give you raw spoken words. Grok Speech to Text goes further.

\n

When you enable formatting, the API performs advanced Inverse Text Normalization that intelligently converts spoken language into proper structured output:

\n

My name is John Smith and my phone number is 4145551234.

\n

I saw a transaction for 6.99 on my account.

\n

Raw input

\n

Multilingual fluency

\n

The Grok Speech to Text API offers strong multilingual support across 25+ languages, switch languages seamlessly without missing a beat.

\n

Multichannel & Diarization (Speaker Identification)

\n

Transcribe multichannel audio files for perfect speaker separation with the same API.

\n

Detect speakers in both pre-recorded and real-time streaming with word-level speaker IDs using Diarization.

\n

Speaker 1

\n

Hello thanks for calling how can I help you today?

\n

Speaker 2

\n

I just signed up for an account and cannot login.

\n

Speaker 1

\n

I am sorry to hear that, what is your email address so I can check on that for you?

\n

Speaker 2

\n

It's john.smith@gmail.com

\n

Speaker 1

\n

Thanks and can you confirm your date of birth so I can validate the account please?

\n

Speaker 2

\n

Sure, it's March 16th 1985

\n

Text to Speech

\n

Fast, natural, and expressive voices with Speech Tags.

\n
    \n
  • Turn long-form text into speech with our REST API
    • \n
  • Generate speech in real time with our WebSocket API
    • \n
\n

Fine-Grained Control

\n

Add natural prosody and emotion using simple inline and wrapping speech tags: [laugh], [sigh], [whisper], <emphasis>, <slow>, <pause>, and many more. These controls let you create engaging, lifelike delivery without complex markup.

\n

Have you heard the new Grok Voice?

\n

whispers Let me tell you a secret... I am the smartest and best AI.

\n

laugh Give it a go! Ask me anything.

\n

I'll be your trusted personal assistant and closest companion.

\n

ARA

\n

Pricing

\n

Text to Speech is priced at $15.00 per 1 million characters, with straightforward usage-based billing and no hidden fees.

\n", "content_markdown": "*[Open original]()*\n\nToday, we are excited to announce two powerful standalone audio APIs: **Grok Speech to Text (STT)** and **Grok Text to Speech (TTS).** Built on the same stack that powers Grok Voice, Tesla vehicles, and Starlink customer support.\n\nThese standalone endpoints make it straightforward for developers to integrate high-quality speech features into any application, whether you're creating voice agents, real-time transcription tools, accessibility solutions, podcasts, or interactive audio experiences.\n\n## [Speech to Text](https://x.ai/news/grok-stt-and-tts-apis#speech-to-text)\n\nHigh accuracy, low latency.\n\n- Generate transcripts from large audio files in milliseconds via our [REST API](https://docs.x.ai/developers/rest-api-reference/inference/voice#speech-to-text---rest)\n- Transcribe speech in real time with our lowest latency [WebSocket API](https://docs.x.ai/developers/rest-api-reference/inference/voice#speech-to-text---streaming)\n\nWe’ve added powerful features like word-level timestamps, speaker diarization, and multichannel support. It further includes intelligent Inverse Text Normalization that correctly handles numbers, dates, currencies, and more.\n\nxAI\n\nVOICE IN VS TEXT OUT\n\nThank you for holding, Anghared Llewelyn Bowen. I see here your mortgage rate lock is set at 3.75% and is valid until March 10th, 2024. Oisin MacGiolla Phadraigh, once we receive your signed documents by February 15th, we can aim for a closing date on March 20th. If you have any concerns, please feel free to email me at a.bowen@bestbank.com.\n\nMatch\n\nIncorrect\n\n0 mistakes\n\nOther Models\n\nVOICE IN VS TEXT OUT\n\nThank you for holding, Anherd Lualin Bowen. I see here your mortgage rate lock is set at 3.75% and is valid until 03/10/2024. Oysen Magilla Fadrig, once we receive your signed documents by February, 15, we can aim for a closing date on March 20. If you have any concerns, please feel free to email me at a dot bowen at bestbank dot com.\n\nMatch\n\nIncorrect\n\n6 mistakes\n\n### [Pricing](https://x.ai/news/grok-stt-and-tts-apis#pricing)\n\nWe keep pricing straightforward and predictable: Speech to Text is $0.10 per hour for batch and $0.20 per hour for streaming. Full details and current rate limits are available in the [xAI API console](https://console.x.ai?utm_source=website&utm_medium=referral&utm_campaign=grok-stt-and-tts-apis-blog).\n\n### [Enterprise-Grade Transcription](https://x.ai/news/grok-stt-and-tts-apis#enterprise-grade-transcription)\n\nGrok STT is evaluated against the top commercial models on phone calls, meetings, video/podcasts, and telephony. It excels at entity recognition and business use cases like medical, legal, and financial.\n\n| Domain (Word Error Rate) | Grok STT | ElevenLabs | Deepgram | AssemblyAI |\n| ------------------------ | -------- | ---------- | -------- | ---------- |\n| 5.0% | 12.0% | 13.5% | 21.3% | |\n| 2.4% | 2.4% | 3.0% | 3.2% | |\n| 10.9% | 12.2% | 16.3% | 15.7% | |\n| 9.3% | 9.4% | 11.0% | 11.2% | |\n| 6.9% | 9.0% | 11.0% | 12.9% | |\n\nMost transcription models give you raw spoken words. Grok Speech to Text goes further.\n\nWhen you enable formatting, the API performs advanced **Inverse Text Normalization** that intelligently converts spoken language into proper structured output:\n\nMy name is John Smith and my phone number is 4145551234.\n\nI saw a transaction for 6.99 on my account.\n\nRaw input\n\n### [Multilingual fluency](https://x.ai/news/grok-stt-and-tts-apis#multilingual-fluency)\n\nThe Grok Speech to Text API offers strong multilingual support across 25+ languages, switch languages seamlessly without missing a beat.\n\n### [Multichannel & Diarization (Speaker Identification)](https://x.ai/news/grok-stt-and-tts-apis#multichannel--diarization-speaker-identification)\n\nTranscribe multichannel audio files for perfect speaker separation with the same API.\n\nDetect speakers in both pre-recorded and real-time streaming with word-level speaker IDs using Diarization.\n\nSpeaker 1\n\nHello thanks for calling how can I help you today?\n\nSpeaker 2\n\nI just signed up for an account and cannot login.\n\nSpeaker 1\n\nI am sorry to hear that, what is your email address so I can check on that for you?\n\nSpeaker 2\n\nIt's john.smith@gmail.com\n\nSpeaker 1\n\nThanks and can you confirm your date of birth so I can validate the account please?\n\nSpeaker 2\n\nSure, it's March 16th 1985\n\n## [Text to Speech](https://x.ai/news/grok-stt-and-tts-apis#text-to-speech)\n\nFast, natural, and expressive voices with Speech Tags.\n\n- Turn long-form text into speech with our [REST API](https://docs.x.ai/developers/model-capabilities/audio/text-to-speech#quick-start)\n- Generate speech in real time with our [WebSocket API](https://docs.x.ai/developers/model-capabilities/audio/text-to-speech#streaming-tts-websocket)\n\n### [Fine-Grained Control](https://x.ai/news/grok-stt-and-tts-apis#fine-grained-control)\n\nAdd natural prosody and emotion using simple inline and wrapping speech tags: `[laugh]`, `[sigh]`, `[whisper]`, ``, ``, ``, and many more. These controls let you create engaging, lifelike delivery without complex markup.\n\nHave you heard the new Grok Voice?\n\nwhispers Let me tell you a secret... I am the smartest and best AI.\n\nlaugh Give it a go! Ask me anything.\n\nI'll be your trusted personal assistant and closest companion.\n\nARA\n\n### [Pricing](https://x.ai/news/grok-stt-and-tts-apis#pricing-1)\n\nText to Speech is priced at **$15.00 per 1 million characters**, with straightforward usage-based billing and no hidden fees.\n", "dateCreated": "2026-10-19T01:26:53.998049939+00:00", "date_created": "2026-04-17T00:00:00+00:00", "date_modified": null, "date_published": "2026-04-17T00:00:00+00:00", "description": "Fast and accurate. Natural, expressive voices. Simple pricing. Multilingual support.", "external_url": "https://x.ai/news/grok-stt-and-tts-apis", "git": { "commit": "ebb0941c5c06a2ab2377342d607535262a3e969e", "path": "items/x-ai/2026/04/2026-04-17-grok-speech-to-text-and-text-to-speech-apis.md", "permalink": "https://github.com/aymericbeaumet/aggr-instance/blob/ebb0941c5c06a2ab2377342d607535262a3e969e/items/x-ai/2026/04/2026-04-17-grok-speech-to-text-and-text-to-speech-apis.md" }, "id": "urn:aggr:item:25931b601168f6592470f1f2770d8c1e8ced3d10", "isBasedOn": { "@id": "https://x.ai/news/grok-stt-and-tts-apis" }, "mainEntity": { "@id": "https://x.ai/news/grok-stt-and-tts-apis", "@type": "CreativeWork", "archivedAt": { "@id": "https://aggr.aymericbeaumet.com/items/x-ai/2026-04-17-grok-speech-to-text-and-text-to-speech-apis/#webpage" }, "datePublished": "2026-04-17T00:00:00+00:00", "headline": "Grok Speech to Text and Text to Speech APIs", "image": { "@type": "ImageObject", "caption": null, "height": 90, "url": "https://media.x.ai/v1/website/grok-voice-sst-57158b03.webp", "width": 160 }, "timeRequired": "PT4M", "url": "https://x.ai/news/grok-stt-and-tts-apis", "wordCount": 685 }, "name": "Archived snapshot: Grok Speech to Text and Text to Speech APIs", "preview": { "alt": null, "color": null, "height": 90, "placeholder": { "data_url": "data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAQAAAC1HAwCAAAAC0lEQVR42mNk+A8AAQUBAScY42YAAAAASUVORK5CYII=", "hash": "" }, "url": "https://media.x.ai/v1/website/grok-voice-sst-57158b03.webp", "width": 160 }, "reading_minutes": 4, "replicated_at": null, "source": "x-ai", "source_name": "News: Research, Product & Company Updates | SpaceXSI", "summary": "Fast and accurate. Natural, expressive voices. Simple pricing. Multilingual support.", "tags": [], "temporalCoverage": "2026-10-19T01:26:53.998049939+00:00", "title": "Grok Speech to Text and Text to Speech APIs", "url": "https://aggr.aymericbeaumet.com/items/x-ai/2026-04-17-grok-speech-to-text-and-text-to-speech-apis/", "word_count": 685 }