Sign in
← AI PulseAug 6, 2026

Wire · news · Multi-source brief

Vercel AI SDK Adds Fish Audio Provider, Enhances ToolLoopAgent and Message Handling

Vercel has released updates to its AI SDK, including a new Fish Audio provider with speech and transcription models, alongside enhancements to the ToolLoopAgent and message regeneration capabilities.

By Illumora Editorial

Source · Aug 6, 2026, 12:58 AM · On Illumora · Aug 6, 2026, 1:08 AM

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 →Vercel AI SDK Changelog — Release @ai-sdk/workflow-harness@1.0.60 · vercel/ai
Save

Vercel has updated its AI SDK, introducing @ai-sdk/fish-audio@3.0.0, which adds a new provider for speech and transcription models. The update also includes several patch changes to the core ai package, version 7.0.54, and other SDK components.

Key Points

  • The @ai-sdk/fish-audio@3.0.0 package introduces a new provider for speech and transcription models.
  • ai@7.0.54 allows ToolLoopAgent prepareCall callbacks to read and override the top-level reasoning option.
  • A defaultInstructionsMiddleware has been added to ai@7.0.54 for applying default language model instructions while preserving call-level overrides.
  • ai@7.0.54 now preserves preceding assistant messages when regenerating a response.
  • @ai-sdk/anthropic@4.0.32 rejects spliced Anthropic generations but permits duplicate message start events for the active message.

Context

According to the Vercel AI SDK changelog, these updates are part of ongoing development across various SDK packages. The changes affect core functionalities related to language model interactions and specific provider integrations, such as Anthropic and the newly added Fish Audio.

Why It Matters

These updates provide developers with more control over language model interactions, particularly in managing instructions and message history. The addition of a new audio provider expands the SDK's capabilities for applications requiring speech and transcription, potentially reducing the need for external integrations.

What To Do

  • Review the updated documentation for @ai-sdk/fish-audio to understand its speech and transcription model capabilities.
  • Examine the ToolLoopAgent prepareCall callbacks to leverage the new reasoning option override.
  • Implement defaultInstructionsMiddleware to manage default language model instructions while allowing call-level customizations.
  • Note the improved message regeneration behavior, which now preserves preceding assistant messages.
  • If using @ai-sdk/anthropic, be aware of the updated handling for spliced generations and duplicate message start events.

Keep Exploring

/atlas/claude-family /techniques/system-user-separation /techniques/output-schema /studio?pack=foundation