Get started

Changelog

November 21, 2025

Dubbing

  • JSON transcript format: Added support for JSON format transcripts in the GET /v1/dubbing/{dubbing_id}/transcript/{language_code} endpoint, returning detailed word-level and character-level timing data via DubbingTranscriptResponseModel.

Agents Platform

  • GPT-5.1 support: Added support for gpt-5.1 and gpt-5.1-2025-11-13 LLM models in agent configurations.
  • Reasoning effort control: Added none option to LLMReasoningEffort for improved control over model reasoning behavior.
  • Agent tool request events: Added agent_tool_request to ClientEvent for better tool interaction tracking in real-time conversations.
  • Out-of-band DTMF: Added use_out_of_band_dtmf flag to PlayDTMFToolConfig for improved telephony integration.
  • LLM model additions: Extended LLM enum with gemini-3-pro-preview for enhanced conversational AI capabilities.

Speech to Text

  • Scribe quota exceeded events: Added quota_exceeded event in SDKs and include_timestamps parameter for better quota management and timestamp control.

Studio

  • Chapter voice tracking: Added voice_ids field to chapter response models for better voice management in multi-voice projects.
  • Project image assets: Introduced ProjectImageResponseModel for image asset support, now included in ProjectResponseModel.assets.
  • Base voices field: Added base_voices field to ProjectResponseModel for improved voice management.

Text to Speech

  • Text normalization control: Added TextNormalisationType enum and text_normalisation_type field across TTS voice settings for fine-grained control over text processing.
  • TTS WebSocket tokens: Extended SingleUseTokenType with tts_websocket for secure WebSocket authentication.

SDK Releases

JavaScript SDK

  • v2.25.0 - Updated with latest API schema changes including JSON dubbing transcripts and GPT-5.1 support
  • v2.24.1 - Added include_timestamps parameter to Scribe API for timestamp control in transcriptions

Python SDK

  • v2.24.0 - Updated with latest API schema changes including JSON dubbing transcripts and GPT-5.1 support
  • v2.23.0 - Added include_timestamps parameter and quota_exceeded event to Scribe API for better quota management

Packages

API

Updated Endpoints

Dubbing

  • GET /v1/dubbing/{dubbing_id}/transcript/{language_code}
    • language path parameter now accepts 'original' value
    • format_type query parameter now supports 'json' (in addition to srt and webvtt)
    • 200 response now includes application/json media type returning DubbingTranscriptResponseModel with:
      • DubbingTranscriptUtterance - Utterance-level data
      • DubbingTranscriptWord - Word-level timing
      • DubbingTranscriptCharacter - Character-level timing
  • Added DubbingModel enum with dubbing_v2 and dubbing_v3 values

Agents Platform

  • Submit batch calling
    • Request body schema updated (backward compatible)
    • Response schema updated (backward compatible)
  • Get batch calling status
    • Response schema updated (backward compatible)
  • Cancel batch calling
    • Response schema updated (backward compatible)
  • Retry batch calling
    • Response schema updated (backward compatible)
  • Get agent settings
    • Response schema updated (backward compatible)
  • Update agent settings
    • Request and response schemas updated (backward compatible)
  • Create agent
    • Request schema updated with improved guardrails structure (breaking change - simplified guardrails to direct reference, removing oneOf)
  • Get agent
    • Response schema updated (breaking change - removed feature-flagged version_id and branch_id fields)
  • Update agent
    • Response schema updated (breaking change - removed feature-flagged version_id and branch_id fields)
  • Simulate conversation
    • Request schema updated (backward compatible)
  • Simulate conversation stream
    • Request schema updated (backward compatible)
  • Get conversation
    • Response schema updated (backward compatible)
  • Client events updated:
    • Added agent_tool_request event type
  • Tool configurations updated:
    • Added use_out_of_band_dtmf to PlayDTMFToolConfig
    • Removed ApiIntegrationWebhookToolConfigExternal-* schemas and their discriminator mappings

Text to Speech

Voice Management

Studio

  • Get project
    • Response schema updated (backward compatible)
    • Added assets field with image support
    • Added base_voices field
  • Add chapter
    • Response schema updated (backward compatible)
    • Added voice_ids field
  • Get chapter
    • Response schema updated (backward compatible)
    • Added voice_ids field
  • Update chapter
    • Response schema updated (backward compatible)
    • Added voice_ids field

Music

Other Updates

Removed Features

  • Removed deprecated eleven_expressive and expressive options from TTS enums