feat: add ForbiddenError, new voice IDs, OpenAI GPT-Live speaker/reasoner, and org limits types - #49
Open
fern-api[bot] wants to merge 3 commits into
Open
fern-api[bot] wants to merge 3 commits into
fern-api[bot] wants to merge 3 commits into
Conversation
fern-api
Bot
force-pushed
the
fern-bot/2026-09-10_21-49-32_753
branch
2 times, most recently
from
September 10, 2026 23:04
dba93cf to
db50444
Compare
fern-api
Bot
changed the title
fern-api
Bot
force-pushed
the
fern-bot/2026-09-10_21-49-32_753
branch
2 times, most recently
from
September 10, 2026 23:47
e82cb5c to
f21c240
Compare
fern-api
Bot
changed the title
fern-api
Bot
changed the title
fern-api
Bot
force-pushed
the
fern-bot/2026-09-10_21-49-32_753
branch
6 times, most recently
from
September 14, 2026 22:47
c14a7a4 to
f2b37f2
Compare
fern-api
Bot
changed the title
fern-api
Bot
force-pushed
the
fern-bot/2026-09-10_21-49-32_753
branch
6 times, most recently
from
September 17, 2026 17:00
1972fe3 to
01c3ae1
Compare
Generated by Fern CLI Version: unknown Generators: - fernapi/fern-typescript-sdk: 3.63.0
…T-Live speaker/reasoner, and org limits types Expand the SDK with several new capabilities: a dedicated ForbiddenError (HTTP 403) is now thrown by all EvalClient methods instead of the generic VapiError, giving callers a typed error to catch. New OpenAI GPT-Live voice IDs (ash, ballad, coral, quartz, ripple, vesper, willow, stone, gleam, meridian, bossa, tempo, beacon, delta, cinder, sage, verse) are added to OpenAiVoiceIdEnum and FallbackOpenAiVoiceIdEnum. Rime AI voice models gain `coda` and `mistv3`, plus seven new voice IDs (Clementine, Walnut, Eyre, Bancroft, Hesse, Beatty, Godfrey). OpenAiModel gains optional `speaker` and `reasoner` fields for GPT-Live configuration, backed by new OpenAiSpeaker, OpenAiReasoner, OpenAiReasonerModel, OpenAiReasonerProvider, and OpenAiReasonerReasoningEffort types. AnthropicBedrockModel gains an optional `fallbackModels` field. New OrgLimitsResponseDto, OrgConcurrencyLimitsDto, and OrgApiLimitsDto types expose org-level rate and concurrency limits. ModelCost gains optional `seconds` and `usageComplete` fields. The InviteUserDtoRoleZero enum gains a `hipaa-special` value, and JsonQueryOnEventsTableOn gains `assistant.knowledgeBase.requestSucceeded`. Key changes: - Add ForbiddenError class and throw it on HTTP 403 across all EvalClient methods - Add 17 new OpenAI voice IDs to OpenAiVoiceIdEnum/FallbackOpenAiVoiceIdEnum; add coda/mistv3 models and 7 new voice IDs to RimeAiVoiceIdEnum/FallbackRimeAiVoiceIdEnum - Add OpenAiSpeaker, OpenAiReasoner, and supporting types; wire into OpenAiModel as optional speaker/reasoner fields - Add AnthropicBedrockModelFallbackModelsItem enum and optional fallbackModels field on AnthropicBedrockModel - Add OrgLimitsResponseDto, OrgConcurrencyLimitsDto, OrgApiLimitsDto; add seconds/usageComplete to ModelCost; add hipaa-special to InviteUserDtoRoleZero 🌿 Generated with Fern
fern-api
Bot
force-pushed
the
fern-bot/2026-09-10_21-49-32_753
branch
from
September 17, 2026 17:03
01c3ae1 to
85e0ccd
Compare
fern-api
Bot
changed the title
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
2.0.1 → 2.1.0
Added
OpenAiReasoner,OpenAiReasonerModel,OpenAiReasonerProvider, andOpenAiReasonerReasoningEffort— new types for configuring OpenAI reasoning models.OpenAiSpeakerandOpenAiSpeakerPersonalityPacksItem— new types for OpenAI speaker personality configuration.OrgApiLimitsDto,OrgConcurrencyLimitsDto, andOrgLimitsResponseDto— new types exposing organization-level API and concurrency limit information.AnthropicBedrockModelFallbackModelsItem— new exported type for Anthropic Bedrock model fallback configuration.UpdateUserRoleDtoRoleZero.HipaaSpecial("hipaa-special") — new role value added to the user role enum.See full changelog