> ## Documentation Index > Fetch the complete documentation index at: https://dragonwingdocs.qualcomm.com/llms.txt > Use this file to discover all available pages before exploring further. # Synthesize speech from text > Converts text into spoken audio using text-to-speech synthesis. ## Features - Multiple voices and languages - Configurable sample rate (44100, 22050, 16000 Hz) - Automatic resampling - Streaming audio output (chunked transfer encoding) ## Sample Rate The TTS engine outputs audio at 44100 Hz by default. If you specify a different `sample_rate`, the audio will be automatically resampled to match your request. ## Example Request ```json { "text": "Hello, how are you today?", "model": "melo-tts-en", "language": "en", "voice": "default", "sample_rate": 44100 } ``` ## Response The response is binary PCM audio data (raw audio, not WAV format) streamed using HTTP chunked transfer encoding. To play the audio, you'll need to convert it to WAV format using the provided `pcm_to_wav.py` script: ```bash python pcm_to_wav.py speech.pcm speech.wav --rate 44100 --channels 1 --bits 16 ``` ## Supported Parameters Check model capabilities via `/tts/models` to see which parameters are supported: - `gender`: Voice gender (if supported) - `style`: Speaking style (if supported) - `sample_rate`: Output sample rate (if supported) - `parameters`: Additional fine-tuning options ## OpenAPI ````yaml /Ubuntu/ai-workflows/api-specs/audio-analytics/openapi.yaml post /tts/synthesize openapi: 3.0.3 info: title: Audio Analytics API version: 1.0.0 description: > REST API providing AI-powered audio processing: speech recognition (ASR), text translation (T2T), and speech synthesis (TTS). ## Services | Service | Endpoint prefix | Description | |---------|----------------|-------------| | ASR | `/transcriptions/` | Whisper-based speech-to-text (file or live WebSocket streaming) | | T2T | `/translations/` | Opus/NLLB text translation (batch supported) | | TTS | `/tts/` | MeloTTS speech synthesis; returns raw PCM audio | ## Audio formats (ASR input) - WAV, 16-bit PCM; 16 kHz mono recommended; max 25 MB ## TTS output - Supported sample rates: 44100, 22050, 16000 Hz (auto-resampled) ## WebSocket streaming sequence ``` App Server |===POST /transcriptions/create================>| |<==200 {session_id, state: asr_initialized}====| | |===WS /stream=================================>| |<== {state: connection_established}===========| | |===WS {transcriptions_session_audio} (loop)===>| |<===WS {transcript.event, speech_start}====| |<===WS {transcript.text.delta, ...}============| (zero or more) |<===WS {transcript.event, speech_end}======| |<===WS {transcript.text.done, ...}============| | |===POST /transcriptions/close=================>| (after transcript.text.done) ``` ## Authentication None required. contact: name: Qualcomm Support Forums url: https://mysupport.qualcomm.com/supportforums/s/ license: name: BSD-3-Clause-Clear url: https://opensource.org/licenses/BSD-3-Clause-Clear servers: - url: http://{device-ip}:{device-port}/audio-analytics/v1/api description: Audio Analytics API Server variables: device-ip: description: IP address and port of the host device running the Audio Analytics API default: localhost device-port: default: '8085' security: [] tags: - name: Health description: Service health and status endpoints - name: Transcriptions description: Speech-to-text audio transcription (ASR) - name: Translations description: Text-to-text translation between languages - name: TTS description: Text-to-speech synthesis - name: WebSocket description: Real-time streaming communication paths: /tts/synthesize: post: tags: - TTS summary: Synthesize speech from text description: > Converts text into spoken audio using text-to-speech synthesis. ## Features - Multiple voices and languages - Configurable sample rate (44100, 22050, 16000 Hz) - Automatic resampling - Streaming audio output (chunked transfer encoding) ## Sample Rate The TTS engine outputs audio at 44100 Hz by default. If you specify a different `sample_rate`, the audio will be automatically resampled to match your request. ## Example Request ```json { "text": "Hello, how are you today?", "model": "melo-tts-en", "language": "en", "voice": "default", "sample_rate": 44100 } ``` ## Response The response is binary PCM audio data (raw audio, not WAV format) streamed using HTTP chunked transfer encoding. To play the audio, you'll need to convert it to WAV format using the provided `pcm_to_wav.py` script: ```bash python pcm_to_wav.py speech.pcm speech.wav --rate 44100 --channels 1 --bits 16 ``` ## Supported Parameters Check model capabilities via `/tts/models` to see which parameters are supported: - `gender`: Voice gender (if supported) - `style`: Speaking style (if supported) - `sample_rate`: Output sample rate (if supported) - `parameters`: Additional fine-tuning options operationId: synthesizeSpeech requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/SynthesizeRequest' example: text: Hello, how are you today? model: melo-tts-en language: en voice: default sample_rate: 44100 output_speaker: false responses: '200': description: Speech synthesized successfully content: application/octet-stream: schema: type: string format: binary description: >- Raw PCM audio data (16-bit little-endian). Not WAV — convert before playback. '400': description: Bad request - invalid input content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '500': description: Internal server error content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' components: schemas: SynthesizeRequest: type: object description: Text-to-speech synthesis request properties: text: type: string description: Text to synthesize into speech example: Hello, how are you today? model: type: string description: TTS model ID example: melo-tts-en language: type: string description: ISO 639-1 language code example: en voice: type: string description: Voice identifier (if model supports multiple voices) example: default gender: type: string description: Voice gender preference (if supported by model) enum: - male - female - neutral example: neutral style: type: string description: Speaking style (if supported by model) example: neutral sample_rate: type: integer description: >- Output sample rate in Hz (if supported by model). Audio will be resampled if different from native rate. example: 44100 parameters: type: object additionalProperties: type: string description: Additional synthesis parameters (e.g., speaking_rate, pitch, gain) example: speaking_rate: '1.0' pitch: '1.0' gain: '0.0' output_speaker: type: boolean description: Output audio data results to speaker example: false required: - text - model ErrorResponse: type: object description: Standard error response structure properties: error: type: object properties: message: type: string description: Human-readable error message example: Invalid request, missing 'file' parameter type: type: string description: Error type or category example: invalid_request_error param: type: string nullable: true description: Parameter related to the error (if applicable) example: file code: type: string nullable: true description: Error code (if applicable) example: null required: - message - type required: - error ````