Sign in
← AI PulseAug 20, 2026

Wire · news · Multi-source brief

xAI Introduces Speech to Text API with REST and Streaming Options

xAI has launched a new Speech to Text API, offering both file-based batch transcription via a REST endpoint and real-time, low-latency transcription through a streaming endpoint, with pricing set at $0.10 per hour for REST and $0.20 per hour for streaming.

By Illumora Editorial

Source · Aug 20, 2026, 3:13 PM · On Illumora · Aug 20, 2026, 4:09 PM

Media from the primary source — shown here so you can stay on Illumora.

Synthesized from multiple allowlisted primaries on the same event. Lanes →

Brief drafted by Illumora’s editorial model from the linked primary source. Ops desk reviews flagged pieces. How we write →

Read the source →xAI Docs — Speech to Text | SpaceXAI Docs
Save

xAI has released a new Speech to Text API, designed to transcribe audio into text. This API provides two primary methods for transcription: a REST endpoint for file-based batch processing and a streaming endpoint for real-time, low-latency transcription. The service was last updated on July 23, 2026, and operates in the us-east-1 region.

Key Points

  • The Speech to Text API supports both REST and streaming transcription modalities.
  • REST transcription is priced at $0.10 per hour, while streaming transcription costs $0.20 per hour.
  • Supported audio formats include WAV, MP3, WebM, OGG, and M4A.
  • The API offers capabilities such as multiple language support and keyterm prompting for domain-specific vocabulary.
  • Streaming transcription includes real-time interim results and Smart Turn end-of-turn detection.
  • Rate limits are 10 requests per second (RPS) for both REST and streaming, with streaming also allowing 100 concurrent sessions per team.

Context

According to xAI, the Speech to Text API is part of a broader suite of voice capabilities, which also includes Speech to Speech, Text to Speech, and Custom Voices. The company also offers a Responses API for interacting with its models, which can store conversation history for up to 30 days. For managing and searching through documents, xAI provides a Collections service, which allows users to upload files and create embedding indexes for semantic search, supporting various MIME types including HTML, PDF, and text files.

Why It Matters

Developers can integrate xAI's Speech to Text API to convert audio content into text, enabling applications that require transcription for analysis, accessibility, or interaction. The availability of both batch and real-time options, along with specific pricing and rate limits, allows builders to plan for cost and performance in their applications.

What To Do

  • Review the pricing details for REST and streaming transcription to estimate costs for your use case.
  • Test the API with various audio formats to ensure compatibility with your source material.
  • Explore the documentation for the Speech to Text Guide to understand implementation details.
  • Note the rate limits for requests per second and concurrent sessions to design for scale.

Keep Exploring

/atlas/**grok**-family /techniques/multimodal-grounding /studio?pack=foundation