Repository navigation
Tags
Tags
chore(main): release 7.18.0 (#827) 🤖 I have created a release *beep* *boop* --- ## [7.18.0](v7.17.0...v7.18.0) (2026-11-10) ### Features * **core:** Preserve unknown Agent V1, Listen V1/V2, and Speak V2 WebSocket messages as raw dictionary payloads instead of dropping them; Listen V1/V2 binary frames are now typed. Responses from `with_raw_response()` expose the underlying `httpx.Response` as `.response`. To avoid replaying a request the server may already have applied, `httpx.RemoteProtocolError` is no longer retried by default; opt in for safe requests with `request_options={"retry_remote_protocol_errors": True}`. ([#826](#826)) ([3b3679c](3b3679c)) ## Highlights - Unknown Agent V1, Listen V1/V2, and Speak V2 WebSocket frames now reach applications as raw dictionary payloads when the SDK does not recognize their variant. - `with_raw_response()` wrappers now expose the underlying `httpx.Response` through `.response`. - `httpx.RemoteProtocolError` retries are opt-in through `request_options={"retry_remote_protocol_errors": True}` to prevent accidental replay of a request that the server may have already applied. --- This PR was generated with [Release Please](https://github.com/googleapis/release-please). See [documentation](https://github.com/googleapis/release-please#release-please). --------- Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Greg Holmes <greg.holmes@deepgram.com>
chore(main): release 7.17.0 (#822) 🤖 I have created a release *beep* *boop* --- ## [7.17.0](v7.16.0...v7.17.0) (2026-11-02) ### Features * **Voice Agent:** Use Deepgram-hosted language models in the Think stage with `ThinkSettingsV1Provider_Deepgram`. Select `think-fast` (requires Model Improvement Program participation) or `phonellm-mini-alpha-2-fp8` (for sessions using `mip_opt_out=True`). The provider supports `temperature`, `reasoning_mode`, and `voice_prompt_opt_out`; use `reasoning_mode="none"` or omit it with phonellm to prevent reasoning text from being spoken. Early Access. ([#821](#821)) ([5c7f319](5c7f319)) ([#823](#823)) ([3280a4a](3280a4a)) --- This PR was generated with [Release Please](https://github.com/googleapis/release-please). See [documentation](https://github.com/googleapis/release-please#release-please). --------- Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Greg Holmes <greg.holmes@deepgram.com>
chore(main): release 7.16.0 (#818) 🤖 I have created a release *beep* *boop* --- ## [7.16.0](v7.15.0...v7.16.0) (2026-10-27) ### Features * **Voice Agent Think Live:** Configure `agent.think_live` with the Deepgram v1 provider; update it during a session with `connection.send_update_think_live(...)`; and receive `ThinkLiveUpdated` and `FrustrationDetected` events. Use `connection.send_inject_dynamic_agent_message(...)` to request a Think Live-generated filler line. `ConversationText` now reports `conversational_behavior` (`default`, `backchannel`, `presence_check`, or `filler`); the service always sends it, while older or self-hosted payloads default to `default` in the Python model. ([#815](#815)) ([0a97e3a](0a97e3a)) * **Flux TTS:** Flux models now support 41 languages and 230 voices. Continue to pass the model as `flux-{voice}-{language}`; text normalization is available for English, German, Dutch, French, Hindi, Italian, Japanese, Portuguese, Russian, and Spanish. ([#815](#815)) ([0a97e3a](0a97e3a)) ### Bug Fixes * **Agent:** Document `ConversationText.conversational_behavior` as always sent, while retaining the `default` fallback for self-hosted and mocked payload compatibility. ([#819](#819)) ([cd8ba29](cd8ba29)) --- This PR was generated with [Release Please](https://github.com/googleapis/release-please). See [documentation](https://github.com/googleapis/release-please#release-please). --------- Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Greg Holmes <greg.holmes@deepgram.com>
chore(main): release 7.15.0 (#814) 🤖 I have created a release *beep* *boop* --- ## [7.15.0](v7.14.0...v7.15.0) (2026-10-23) ### Features * **Listen V1 / Nova-3 multilingual:** Add optional language_hint support for synchronous and asynchronous URL/file transcription and WebSocket connections. Pass one BCP-47 hint as a string or several as a list; hints bias detection when model=nova-3 and language=multi. Transcription alternatives now expose typed languages and normalized languages_hinted fields, with per-word and utterance language metadata. ([#813](#813)) ([b474446](b474446)) --- This PR was generated with [Release Please](https://github.com/googleapis/release-please). See [documentation](https://github.com/googleapis/release-please#release-please). --------- Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Greg Holmes <greg.holmes@deepgram.com>
chore(main): release 7.14.0 (#808) 🤖 I have created a release *beep* *boop* --- ## [7.14.0](v7.13.0...v7.14.0) (2026-10-20) ### Features * **Voice Agent:** Send protocol-transparent control frames with sync or async `connection.send_raw(...)`. Dictionary payloads are serialized without model validation; pre-serialized JSON strings are sent unchanged. * **Listen V1:** Receive typed `ListenV1ConfigureSuccess` and `ListenV1ConfigureFailure` responses after `connection.send_configure(ListenV1Configure(...))`, including failure codes for unsupported or over-limit keyterms. ### Bug Fixes * **Voice Agent:** Clarify ForceEndTurn availability for hosted and self-hosted deployments. The example now reports `FORCE_END_TURN_UNSUPPORTED` and waits for the final outcome before closing the connection. ## Validation - Source PR CI passed across Python 3.10 through 3.13. - #803: `poetry run pytest` passed with 1,075 tests and 4 skips; mypy and Ruff passed. - #789: targeted socket-client tests, mypy, and Ruff passed. - #788: ForceEndTurn regression coverage passed. --- This PR was generated with [Release Please](https://github.com/googleapis/release-please). See [documentation](https://github.com/googleapis/release-please#release-please). --------- Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Greg Holmes <greg.holmes@deepgram.com>
chore(main): release 7.13.0 (#800) 🤖 I have created a release *beep* *boop* --- ## [7.13.0](v7.12.0...v7.13.0) (2026-10-08) ### Features * **Listen V1:** Reconfigure active Nova-3 streams without reconnecting with `connection.send_configure(ListenV1Configure(...))`, including keyterms and numerals. Configure rejections arrive as typed `ListenV1Error` responses. * **Voice Agent:** Exchange experimental custom Think-provider payloads with `send_custom_to_think_provider(AgentV1CustomToThinkProvider(...))` and `AgentV1CustomFromThinkProvider` responses. This requires a configured custom Think-provider WebSocket endpoint. ## Validation - `poetry run pytest -rP --cov=deepgram --cov-branch --cov-report=xml --cov-report=term-missing .` (1,075 passed, 4 skipped; 94.63% coverage) - Ruff, mypy, and example compilation passed. - Live smoke verified Listen V1 Configure plus Voice Agent settings, KeepAlive, and prompt updates. - `examples/19-transcription-live-reconfigure.py` completed against the live API. --- This PR was generated with [Release Please](https://github.com/googleapis/release-please). See [documentation](https://github.com/googleapis/release-please#release-please). --------- Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Greg Holmes <greg.holmes@deepgram.com>
chore(main): release 7.12.0 (#798) 🤖 I have created a release *beep* *boop* --- ## [7.12.0](v7.11.0...v7.12.0) (2026-10-01) ### Features * **Flux TTS controls:** Add inline pause markers for Flux batch synthesis and IPA pronunciation overrides for Flux batch, Flux WebSocket, and Aura-2. Pronunciation is Early Access; pauses are Flux batch-only. See [Speed, Pause, Pronunciation](https://developers.deepgram.com/docs/tts-voice-controls). ([#797](#797)) ([d2b5514](d2b5514)) * **TextBuilder migration:** Emit the escaped marker syntax Flux accepts: pauses as `\{pause:500ms\}` and pronunciations as `\{"word": "...", "pronounce": "<IPA>"\}`. The 7.11.0 forms are rejected or ignored by `/v2/speak`, so upgrade when using TextBuilder with Flux TTS. * **TextBuilder validation:** Match Flux batch limits: pauses must be 500-3000 ms in 100 ms increments, with at most eight per request. `pause()`, `from_ssml()`, and `build()` now raise `ValueError` for malformed, out-of-range, off-grid, or mixed pause-and-pronunciation controls before sending a request the API would reject. * **Listen v2 (Flux):** Add typed `Warning` responses while retaining dict-style response access during the v7 transition. ### Compatibility * **Topics and Intents:** Type the direct API `segments` response shape while retaining deprecated `results` facades, legacy import paths, and legacy construction throughout v7. --- This PR was generated with [Release Please](https://github.com/googleapis/release-please). See [documentation](https://github.com/googleapis/release-please#release-please). --------- Co-authored-by: Corey Weathers <corey.weathers@deepgram.com> Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
chore(main): release 7.11.0 (#795) 🤖 I have created a release *beep* *boop* --- ## [7.11.0](v7.10.0...v7.11.0) (2026-09-23) ### Features * **Listen v2 (Flux):** change numerals during an active connection with `connection.send_configure(ListenV2Configure(numerals=True))`. Numerals convert written numbers to numerical format for turns transcribed after the update. ([#794](#794)) ([c7c1b3f](c7c1b3f)) --- This PR was generated with [Release Please](https://github.com/googleapis/release-please). See [documentation](https://github.com/googleapis/release-please#release-please). --------- Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Greg Holmes <greg.holmes@deepgram.com>
chore(main): release 7.10.0 (#791) 🤖 I have created a release *beep* *boop* --- ## [7.10.0](v7.9.0...v7.10.0) (2026-09-17) ### Features * **Voice Agent:** Add typed `FunctionCallCancelled` WebSocket events. Events identify function calls that are no longer valid; do not send a `FunctionCallResponse` for the listed call IDs. ([#790](#790)) ([7f5b642](7f5b642)) * **Voice Agent:** Add the optional `defer_until_eot` function setting. When enabled, it holds a function call until the user's turn is confirmed and discards the deferred call if the turn resumes. Defaults to `false`. ([#790](#790)) ([7f5b642](7f5b642)) --- This PR was generated with [Release Please](https://github.com/googleapis/release-please). See [documentation](https://github.com/googleapis/release-please#release-please). --------- Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Greg Holmes <greg.holmes@deepgram.com>
PreviousNext